© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43618
    Prev
    Next
    INDEX
    Explanations

    java language and util classes

    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
     in
    -1.88
    …)
    -1.73
     This
    -1.66
    …]
    -1.62
    );
    -1.62
    遄
    -1.56
     schien
    -1.51
     came
    -1.51
    ⁎
    -1.50
    })$.
    -1.49
    POSITIVE LOGITS
     jednej
    1.80
    镲
    1.72
     exceedingly
    1.63
     sogen
    1.62
    instead
    1.62
     elegantly
    1.59
    Compared
    1.56
     hebben
    1.55
    considering
    1.55
     ofte
    1.53
    Activations Density 0.003%

    No Known Activations