© 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. 14212
    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
    ragende
    -1.03
    hemd
    -0.96
     aiuta
    -0.95
     cimetière
    -0.93
    Zutaten
    -0.92
     pouvez
    -0.92
    AMOUNT
    -0.91
    薆
    -0.91
    夘
    -0.90
     mercredi
    -0.90
    POSITIVE LOGITS
     Crisis
    0.93
    riedenheit
    0.93
     forecasts
    0.90
    宦
    0.89
    君子
    0.88
     />}
    0.85
     Кри
    0.85
    ző
    0.85
    on
    0.85
    bin
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.