© 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. 86554
    Prev
    Next
    INDEX
    Explanations

    Raptor, MCC, ATC, Payne

    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
    乆
    -3.50
    鈇
    -3.42
    鱨
    -3.39
    geſ
    -3.13
    韡
    -3.08
    彣
    -3.06
    ейчас
    -2.98
    땃
    -2.88
    荩
    -2.81
    ción
    -2.78
    POSITIVE LOGITS
    b
    3.28
    ↵
    3.00
    H
    2.98
    o
    2.72
    en
    2.66
    K
    2.63
    or
    2.59
    );
    2.52
    J
    2.47
    re
    2.45
    Activations Density 0.003%

    No Known Activations