© 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. 85012
    Prev
    Next
    INDEX
    Explanations

    Whether or not clauses

    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
    na
    -2.05
    。
    -1.98
    ,"
    -1.94
     rests
    -1.85
    ".
    -1.80
     दोनों
    -1.77
     '
    -1.73
     resembles
    -1.69
    delijk
    -1.69
     relates
    -1.68
    POSITIVE LOGITS
     atrav
    1.75
    ໊
    1.69
     pequenas
    1.64
     beschlossen
    1.61
     Whether
    1.61
     it
    1.61
     maanden
    1.59
    にほんブログ村
    1.57
    锜
    1.55
    啭
    1.48
    Activations Density 0.006%

    No Known Activations