© 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. 34-GEMMASCOPE-RES-131K
    7. 64189
    Prev
    Next
    INDEX
    Explanations

    Jal, Al, Zal beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    比特
    -0.82
     terci
    -0.82
    жидан
    -0.77
     quelques
    -0.77
    buhan
    -0.76
    viamo
    -0.74
    onComplete
    -0.73
    NSP
    -0.73
     اصلاح
    -0.73
    ḏ
    -0.72
    POSITIVE LOGITS
     Jal
    0.88
     jal
    0.85
    评价
    0.73
    Jal
    0.70
     Kier
    0.69
    climate
    0.68
    nul
    0.68
    アンケート
    0.66
     either
    0.65
    無料で
    0.65
    Activations Density 0.009%

    No Known Activations