© 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. 85182
    Prev
    Next
    INDEX
    Explanations

    staging events or performances

    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
    5
    -1.95
     présidenti
    -1.80
    姈
    -1.77
     概要
    -1.73
    2
    -1.73
    蛱
    -1.72
     Garantía
    -1.70
     intitulée
    -1.70
    3
    -1.67
    6
    -1.63
    POSITIVE LOGITS
     We
    2.20
     –
    1.94
    我们
    1.88
    __":
    1.77
    ريكية
    1.72
    釙
    1.70
    鞮
    1.70
     staged
    1.69
    ޙ
    1.69
     a
    1.68
    Activations Density 0.006%

    No Known Activations