© 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. 19121
    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
     penyanyi
    -1.08
    <0xF4>
    -1.00
    руб
    -1.00
     だっ
    -0.97
    смо
    -0.95
     الأولى
    -0.95
    шь
    -0.95
     главе
    -0.94
    вані
    -0.94
    етка
    -0.92
    POSITIVE LOGITS
    鬨
    0.99
    Sự
    0.96
     slutet
    0.96
    ométrie
    0.96
     keinen
    0.93
     extérieur
    0.93
     viktigt
    0.93
     vermittelt
    0.93
     results
    0.92
    reeze
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.