© 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. 71864
    Prev
    Next
    INDEX
    Explanations

    code delimiters and foreign words

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

    The neuron is activated by numeric literal tokens (integer constants) in code.

    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
     supplémentaire
    -1.09
    licante
    -1.03
    namental
    -0.98
    ologische
    -0.95
    を見せて
    -0.95
     Désolé
    -0.94
    INARY
    -0.93
     muñeco
    -0.93
     mence
    -0.92
     مُعرِّف
    -0.92
    POSITIVE LOGITS
    ↵↵
    1.03
    readFileSync
    0.82
     stră
    0.81
     على
    0.80
     których
    0.80
     الشباب
    0.80
     सबसे
    0.79
     sollte
    0.78
     kommt
    0.77
    tablissements
    0.77
    Activations Density 0.003%

    No Known Activations