© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20181
    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
    マチ
    -1.27
    
    -1.18
     suelen
    -1.16
     leſs
    -1.16
     aseguran
    -1.16
    髡
    -1.15
    神
    -1.14
     vuelva
    -1.12
     funcionan
    -1.12
     útiles
    -1.11
    POSITIVE LOGITS
    We
    1.05
     are
    0.99
    “
    0.98
    近年来
    0.94
    (())
    0.94
     in
    0.93
    Sale
    0.92
    refreshToken
    0.90
     as
    0.89
    寒冷
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.