© 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. 129117
    Prev
    Next
    INDEX
    Explanations

    ow sounds and related words

    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
    R
    -3.34
    2
    -3.19
    In
    -3.16
    3
    -3.14
    Of
    -3.13
    What
    -3.08
    ”,
    -3.06
    B
    -3.02
    U
    -3.00
    Perhaps
    -2.98
    POSITIVE LOGITS
    圌
    3.09
    馓
    3.02
    褔
    2.73
    讦
    2.73
    electrical
    2.70
    暃
    2.69
    嚶
    2.67
    埸
    2.58
    昃
    2.58
    苌
    2.56
    Activations Density 0.006%

    No Known Activations