© 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. 58649
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     zowel
    -1.34
    忤
    -1.20
    хані
    -1.15
    肄
    -1.08
     начинает
    -1.07
    notated
    -1.07
     Both
    -1.07
    恃
    -1.06
    both
    -1.04
    віти
    -1.04
    POSITIVE LOGITS
    ÜN
    1.27
     précisé
    1.27
    Jetzt
    1.23
    很多
    1.19
     entret
    1.15
     MANY
    1.14
     souligné
    1.13
    dingen
    1.13
    چند
    1.12
    Viele
    1.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.