© 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. 22-GEMMASCOPE-RES-131K
    7. 36700
    Prev
    Next
    INDEX
    Explanations

    function calls and assignments

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

    This neuron fires on function‐related code markers—e.g. the “Functions” section header and Go function signatures (like “func LogLevel() int”).

    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
     also
    -1.06
     Gebiet
    -1.01
     Bewertungen
    -0.94
     Berechnung
    -0.92
     aquella
    -0.91
     erweiter
    -0.90
     sogen
    -0.85
     Wirken
    -0.84
     possibilidades
    -0.83
     enough
    -0.83
    POSITIVE LOGITS
     miele
    1.10
     oktober
    1.10
     januari
    1.08
    #/
    1.03
     häl
    1.02
     toki
    1.00
     propria
    0.98
     hilfiger
    0.98
    ☀
    0.97
     bensin
    0.96
    Activations Density 0.004%

    No Known Activations