© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84470
    Prev
    Next
    INDEX
    Explanations

    convolutional layer padding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    └──
    -0.78
     final
    -0.76
     Malta
    -0.73
     Kry
    -0.72
     sof
    -0.71
    шень
    -0.70
    ági
    -0.70
    PostConstruct
    -0.68
    Kry
    -0.68
    flowing
    -0.68
    POSITIVE LOGITS
    padding
    1.36
     padding
    1.35
     dilated
    1.15
    setPadding
    1.11
     Padding
    1.07
     dilation
    1.01
     pad
    0.99
    dil
    0.98
    Pads
    0.97
    Padding
    0.93
    Activations Density 0.012%

    No Known Activations