© 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. 34-GEMMASCOPE-RES-131K
    7. 107482
    Prev
    Next
    INDEX
    Explanations

    copyright and licenseReserved

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

    The neuron fires strongly on code‐comment “header” tokens—e.g. comment delimiters (/*, */), section headings (Abstract, Environment), license markers, and other metadata in source‐file comment blocks.

    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
    pfel
    -0.73
    XICO
    -0.73
     Forward
    -0.72
     gute
    -0.72
     Certificate
    -0.72
     Punjab
    -0.70
     Copenhagen
    -0.70
    ConfigService
    -0.70
    garmin
    -0.70
    boundaries
    -0.69
    POSITIVE LOGITS
     lé
    0.71
    歷
    0.69
     краски
    0.69
    期間限定
    0.68
     рисо
    0.67
     icono
    0.66
     carica
    0.66
     needful
    0.65
    ポスト
    0.65
     trouble
    0.63
    Activations Density 0.019%

    No Known Activations