© 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. 8865
    Prev
    Next
    INDEX
    Explanations

    introduces specifics or lists

    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
    bonsoir
    -1.42
    );
    -1.34
     also
    -1.30
    Lundi
    -1.29
    坚持
    -1.27
    ▟
    -1.26
    푙
    -1.23
    ).
    -1.22
     outputStream
    -1.22
    ဴ
    -1.21
    POSITIVE LOGITS
     that
    1.60
     robić
    1.59
     which
    1.48
     inginkan
    1.48
     toalla
    1.46
     your
    1.45
     doesn
    1.43
     verrou
    1.42
    któ
    1.39
     zwier
    1.39
    Activations Density 0.083%

    No Known Activations