© 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. 44358
    Prev
    Next
    INDEX
    Explanations

    code structure or names

    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
    一旁的
    -1.67
     longtime
    -1.66
     for
    -1.66
    when
    -1.65
    ?"
    -1.64
    pastebin
    -1.63
     Конечно
    -1.60
     Both
    -1.59
     What
    -1.55
     by
    -1.54
    POSITIVE LOGITS
    Hmmm
    1.72
    ↵↵
    1.65
     "];
    1.55
    ників
    1.46
    tivamente
    1.45
     milliard
    1.44
    payers
    1.44
    </em>
    1.42
     entusias
    1.41
     этапе
    1.40
    Activations Density 0.000%

    No Known Activations