© 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. 8014
    Prev
    Next
    INDEX
    Explanations

    CMake build scripts

    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
     That
    -2.61
    "
    -2.55
    ).
    -2.44
    );
    -2.28
    </h2>
    -2.25
     ที่
    -2.09
    も
    -2.06
    ↵
    -2.03
    ();
    -2.02
     że
    -1.97
    POSITIVE LOGITS
    幛
    2.16
     eşofman
    2.06
    闞
    2.03
    ਃ
    1.98
    羕
    1.95
    苌
    1.86
     maravill
    1.84
    
    1.82
    ﮕ
    1.82
     itſelf
    1.82
    Activations Density 0.004%

    No Known Activations