© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30053
    Prev
    Next
    INDEX
    Explanations

    public keyword in code

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

    This neuron activates on source‐code declaration keywords and the leading indentation before them (e.g. “public,” “static,” “class,” “namespace,” “export,” etc.), i.e. on top‐level code declarations.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    private
    -1.19
    protected
    -1.11
     myös
    -1.03
     protected
    -0.91
    事も
    -0.88
    了一個
    -0.88
    PRIVATE
    -0.88
    void
    -0.87
     private
    -0.84
     również
    -0.83
    POSITIVE LOGITS
    public
    1.18
    pub
    0.99
    export
    0.93
     public
    0.91
     publik
    0.90
     are
    0.88
    میل
    0.87
     pub
    0.83
     publie
    0.83
     offent
    0.81
    Activations Density 0.020%

    No Known Activations