© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14004
    Prev
    Next
    INDEX
    Explanations

    static public methods

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

    This neuron detects programming‐language declaration keywords—particularly access modifiers or storage‐class specifiers such as “public” and “static.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     superbes
    -1.50
     bisous
    -1.48
     rayures
    -1.45
     Comédie
    -1.44
     menetap
    -1.33
     oublié
    -1.29
     soucis
    -1.27
     saveur
    -1.27
     fidé
    -1.27
     verres
    -1.26
    POSITIVE LOGITS
     will
    1.74
     to
    1.63
     when
    1.51
    es
    1.41
    b
    1.32
    st
    1.31
    is
    1.28
    os
    1.28
    ar
    1.27
     would
    1.27
    Activations Density 0.002%

    No Known Activations