© 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. 128405
    Prev
    Next
    INDEX
    Explanations

    relative path imports

    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
    '
    -3.75
    >
    -2.31
    </h4>
    -2.02
    He
    -1.95
    </td>
    -1.95
    U
    -1.88
    </h5>
    -1.88
    \
    -1.88
    </em>
    -1.85
    );
    -1.83
    POSITIVE LOGITS
    沨
    2.22
    峮
    2.16
    ";
    2.14
    ケモン
    2.03
     heath
    2.02
    鯪
    1.98
    镦
    1.96
    ajuku
    1.95
    agreb
    1.90
    無い
    1.89
    Activations Density 0.005%

    No Known Activations