© 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. 41786
    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
    ੀ
    -1.03
    ས
    -0.94
    ted
    -0.93
    llen
    -0.91
    ь
    -0.90
    heim
    -0.90
     vigueur
    -0.90
    ೯
    -0.90
    럿
    -0.88
     raptor
    -0.88
    POSITIVE LOGITS
     that
    0.98
     why
    0.93
    ージェ
    0.92
    出来ました
    0.91
     today
    0.91
     keiner
    0.90
    ও
    0.89
    ƫ
    0.86
     these
    0.85
     今日
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.