© 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. 106004
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    $
    -3.61
    In
    -3.09
    er
    -2.89
    P
    -2.84
    le
    -2.80
    an
    -2.67
    o
    -2.63
    es
    -2.56
    {'
    -2.50
    Taking
    -2.44
    POSITIVE LOGITS
    archiwizowane
    2.70
    
    2.66
    ぶつ
    2.52
     hardy
    2.42
     Перейти
    2.41
    ’
    2.36
     Dingen
    2.33
    }*/
    2.30
     aisladas
    2.27
    
    2.27
    Activations Density 0.015%

    No Known Activations