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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64302
    Prev
    Next
    INDEX
    Explanations

    programming keywords and types

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on long runs of whitespace (indenting or padding spaces).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ството
    -1.02
    tifie
    -1.01
     Ceinture
    -1.01
    ünste
    -0.99
     EARL
    -0.97
     torebka
    -0.96
     вашем
    -0.96
     всички
    -0.95
    一人で
    -0.94
    関する
    -0.93
    POSITIVE LOGITS
    public
    2.16
     public
    1.85
    private
    1.82
     if
    1.57
     private
    1.53
    return
    1.50
    protected
    1.45
    if
    1.37
     void
    1.34
     function
    1.15
    Activations Density 0.011%

    No Known Activations