© 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. 34-GEMMASCOPE-RES-131K
    7. 47876
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation in formulas

    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_34/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
     שול
    -0.91
     gegenwär
    -0.81
     omo
    -0.81
     Arrangement
    -0.75
     einzelnen
    -0.75
     jungen
    -0.73
    わけではない
    -0.73
    enumeration
    -0.72
    етесь
    -0.70
    quetas
    -0.69
    POSITIVE LOGITS
     rewritten
    0.95
     formula
    0.94
     bieg
    0.89
     Público
    0.87
     équ
    0.83
     pidana
    0.83
    ゼン
    0.82
    )-(
    0.82
    aure
    0.82
     expression
    0.81
    Activations Density 0.003%

    No Known Activations