© 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. 33455
    Prev
    Next
    INDEX
    Explanations

    questions and code symbols

    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_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
    mijn
    -0.98
     فقط
    -0.94
    مث
    -0.93
    ysl
    -0.91
     perché
    -0.89
    ៩
    -0.88
    ▻
    -0.88
    vde
    -0.86
     because
    -0.86
     dátum
    -0.85
    POSITIVE LOGITS
    谚
    1.16
    անո
    1.02
     oídos
    1.00
    外观
    0.98
     representa
    0.98
    guien
    0.96
    üğ
    0.96
     suced
    0.96
     Heute
    0.95
     없습니다
    0.93
    Activations Density 0.000%

    No Known Activations