© 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. 8873
    Prev
    Next
    INDEX
    Explanations

    symbols, characters,

    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
     is
    -2.63
     it
    -2.56
     '
    -2.38
     "-
    -1.99
     o
    -1.95
    ！”
    -1.94
     из
    -1.92
     The
    -1.91
     ah
    -1.90
     что
    -1.88
    POSITIVE LOGITS
    糶
    2.28
     ส์
    2.17
     ACKNOWLEDGMENTS
    2.14
     diskusi
    2.06
    Interestingly
    2.03
    穡
    2.00
    Regarding
    1.95
    บน
    1.94
     内衣
    1.94
     SYMBOL
    1.93
    Activations Density 0.013%

    No Known Activations