© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102701
    Prev
    Next
    INDEX
    Explanations

    software license URLs

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

    The neuron detects copyright and license header metadata in source‐code comments, such as copyright notices, years, and license names.

    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
    Fam
    -0.85
    ENEF
    -0.85
    //};
    -0.84
    ")->
    -0.84
     droga
    -0.79
    托管
    -0.78
     veux
    -0.77
    ERICAN
    -0.77
     pove
    -0.77
     erhalten
    -0.76
    POSITIVE LOGITS
    རྒྱ
    0.83
    Technologie
    0.79
     Eclipse
    0.76
    ゴル
    0.73
    quante
    0.72
    Blocked
    0.71
    jeev
    0.70
     Aged
    0.68
    マラ
    0.68
    hela
    0.68
    Activations Density 0.196%

    No Known Activations