© 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. 7447
    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
    and
    -1.12
    peka
    -0.98
    вели
    -0.96
    别人的
    -0.88
     liknande
    -0.86
    cir
    -0.86
     samochodu
    -0.84
    ឬ
    -0.83
    where
    -0.83
    m
    -0.82
    POSITIVE LOGITS
     apetito
    1.09
    rildi
    0.99
    nadequate
    0.97
     apagar
    0.95
    listdir
    0.94
     habilitar
    0.94
    bolistas
    0.93
    iddhar
    0.93
    columnwidth
    0.93
     Swe
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.