© 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. 75514
    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
    strans
    -0.92
    adá
    -0.92
     long
    -0.91
    МЕ
    -0.91
    laag
    -0.90
     on
    -0.89
     infamous
    -0.86
    träd
    -0.86
    komen
    -0.83
    க
    -0.83
    POSITIVE LOGITS
    绷
    0.98
    鹂
    0.97
     şimdi
    0.95
     situações
    0.93
    ܜ
    0.93
     berättar
    0.93
     ocorrer
    0.92
     ocorreu
    0.91
     supri
    0.90
     doesn
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.