© 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. 127261
    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
     depicts
    -0.96
     the
    -0.96
    <0x90>
    -0.91
     hablamos
    -0.87
     pantalon
    -0.87
     departe
    -0.86
     hommage
    -0.85
     anivers
    -0.81
     ничего
    -0.81
     modèle
    -0.80
    POSITIVE LOGITS
    ONU
    1.10
    NVIDIA
    1.06
     BYU
    0.98
     를
    0.97
    雋
    0.97
     détaillé
    0.96
    ุต
    0.95
    jooq
    0.94
    ashing
    0.93
    inerario
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.