© 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. 102526
    Prev
    Next
    INDEX
    Explanations

    code license headers

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

    The neuron strongly fires on tokens in file‐header comment blocks (license, copyright, author, and metadata lines).

    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
     drown
    -0.71
    ellis
    -0.71
     Bezirks
    -0.70
    كلة
    -0.66
     Konzer
    -0.65
     Ahead
    -0.65
    caled
    -0.64
    cina
    -0.64
     settembre
    -0.63
     הספר
    -0.63
    POSITIVE LOGITS
     unités
    0.77
    Castle
    0.75
     Roper
    0.73
    toler
    0.73
     seules
    0.73
    iry
    0.71
     voltou
    0.71
    PHONE
    0.71
     Designed
    0.70
    ſs
    0.69
    Activations Density 0.038%

    No Known Activations