© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 832
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric tokens and numeric identifiers in code (e.g. line‐number markers, numeric literals, and code constants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     if
    0.63
    다면
    0.61
    あまり
    0.60
     laterales
    0.57
    if
    0.57
    ֑
    0.54
     montañas
    0.54
    <img>
    0.54
     위해서는
    0.54
     tengah
    0.53
    POSITIVE LOGITS
    public
    1.67
     public
    1.52
    private
    1.41
     private
    1.20
    static
    1.20
    protected
    1.18
    void
    1.14
     static
    1.12
     void
    1.11
    /**
    1.02
    Activations Density 0.004%

    No Known Activations