© 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. 4350
    Prev
    Next
    INDEX
    Explanations

    books and series

    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
    ENSATION
    -0.98
     useful
    -0.93
    utuhkan
    -0.92
    ドキュ
    -0.91
    Docs
    -0.91
     our
    -0.91
    Postcode
    -0.88
    锂
    -0.88
     muhimu
    -0.87
     procedures
    -0.87
    POSITIVE LOGITS
     series
    2.25
     book
    1.69
     books
    1.61
    series
    1.57
     authors
    1.43
    シリーズ
    1.41
     readers
    1.41
     SERIES
    1.38
    Series
    1.38
     Series
    1.37
    Activations Density 0.053%

    No Known Activations