© 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. 58977
    Prev
    Next
    INDEX
    Explanations

    how well something is done

    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
    杙
    -1.59
    稣
    -1.52
    驺
    -1.47
    罴
    -1.46
    盦
    -1.46
    řízen
    -1.46
    </tfoot>
    -1.46
    璈
    -1.41
    ⤥
    -1.38
    〤
    -1.38
    POSITIVE LOGITS
    ');
    2.06
    ">
    2.03
    ");
    1.98
    9
    1.80
    8
    1.70
    7
    1.70
    .”
    1.63
    ());
    1.60
    _
    1.55
    但
    1.46
    Activations Density 0.018%

    No Known Activations