© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84289
    Prev
    Next
    INDEX
    Explanations

    visualization and visceral terms

    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
    ‘
    -2.72
    t
    -2.69
    ;
    -2.48
     zahlreiche
    -2.45
    their
    -2.34
    ,’
    -2.31
    絰
    -2.30
     می‌توان
    -2.19
     ―
    -2.19
    “,
    -2.19
    POSITIVE LOGITS
     这
    3.25
     '
    3.14
     "
    2.81
    ésil
    2.80
    êmio
    2.78
     glaring
    2.67
    ে
    2.50
    冧
    2.45
    ?...
    2.45
    و
    2.44
    Activations Density 0.006%

    No Known Activations