Can i use the 'activations' function to get the output of a layer during the training of a CNN

Hi experts,

Can i use the 'activations' function to get the output of a layer during the training of a CNN. What i have read is that it can be applied to an already trained CNN. Actually, i am using mobilenetv2 for an image classification problem and i want to get the output of last fully connected layer during training phase, so i can store it in a variable in my workspace and work on it. Is there any way to do that?

Thanks