© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72095
    Prev
    Next
    INDEX
    Explanations

    button click

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

    The neuron is triggering on code tokens that name GUI buttons—i.e. identifiers beginning with “btn_” (button control 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_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
     basit
    -1.13
    文化財
    -1.03
     barva
    -1.01
    哈哈哈哈
    -0.97
    雰囲気が
    -0.94
    fotografia
    -0.94
    瑣
    -0.92
    administration
    -0.91
    前は
    -0.91
    举动
    -0.91
    POSITIVE LOGITS
    チョコ
    0.99
     caffè
    0.98
    endsection
    0.97
     tudi
    0.95
    》、《
    0.94
     rotación
    0.94
     ゴールド
    0.93
    OK
    0.93
     ثبت
    0.92
    领
    0.92
    Activations Density 0.003%

    No Known Activations