© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11935
    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
    UAWEI
    -1.04
    PRES
    -1.02
     Vorsitzender
    -1.00
    ctivos
    -0.98
    JUNE
    -0.97
    ”—
    -0.94
     pyta
    -0.94
    atzen
    -0.93
    }=\
    -0.91
    stals
    -0.88
    POSITIVE LOGITS
     because
    0.96
     besök
    0.96
    価格は
    0.94
    ﾈ
    0.93
    ですよ
    0.91
     даже
    0.91
     during
    0.90
     öppna
    0.89
     аз
    0.88
    兑换
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.