© 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. 10-GEMMASCOPE-RES-131K
    7. 99927
    Prev
    Next
    INDEX
    Explanations

    registration process, instructions, creep, letter

    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_10/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
     เรา
    -1.87
    🫥
    -1.81
     อาหาร
    -1.79
    valentino
    -1.74
     Erkrank
    -1.73
    🫕
    -1.67
    gilet
    -1.66
    pantalon
    -1.66
    🫓
    -1.66
     моей
    -1.65
    POSITIVE LOGITS
    шње
    2.14
     塗装
    2.13
     or
    1.95
    靱
    1.73
    semantics
    1.70
     the
    1.68
    <tr>
    1.67
     државе
    1.62
    ֶּ
    1.59
     uitzicht
    1.55
    Activations Density 0.016%

    No Known Activations