© 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. 25385
    Prev
    Next
    INDEX
    Explanations

    highest common factor

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

    The neuron flags terms and phrases having to do with mathematical divisibility and factors (e.g. “divide,” “multiple,” “factor”).

    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
     mlu
    -0.88
    heri
    -0.83
     then
    -0.82
     FEAR
    -0.81
    strSql
    -0.80
     either
    -0.79
    urally
    -0.78
    –¿
    -0.77
    Quel
    -0.77
    жено
    -0.77
    POSITIVE LOGITS
     jopa
    1.00
    聳
    0.94
     emberek
    0.92
    鈎
    0.91
     尔
    0.91
     miljoen
    0.90
    などの
    0.89
     Knochen
    0.88
     whatsoever
    0.87
    參考資料
    0.86
    Activations Density 0.089%

    No Known Activations