© 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. 69372
    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
     jouent
    -1.01
     sähkö
    -0.96
     of
    -0.96
     Therefore
    -0.96
     suivent
    -0.93
     步骤
    -0.90
     Gedicht
    -0.89
    胰
    -0.87
    拖
    -0.87
     Furthermore
    -0.85
    POSITIVE LOGITS
     techniczne
    1.00
     resemble
    0.97
    ksessa
    0.96
    IBLES
    0.94
     també
    0.93
    讀書
    0.93
    同じ
    0.92
    Otras
    0.91
    مشخصات
    0.89
    ksesta
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.