© 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. 85469
    Prev
    Next
    INDEX
    Explanations

    specifics

    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
    ({
    -1.78
    ;
    -1.70
    新
    -1.66
     aggravated
    -1.52
    "));
    -1.45
    ﻂ
    -1.45
    ನ
    -1.40
    𝑫
    -1.39
    ,”
    -1.38
    ));
    -1.38
    POSITIVE LOGITS
     details
    1.92
     detalhes
    1.73
    </strong>
    1.71
     detail
    1.63
    葑
    1.57
     деталей
    1.53
    and
    1.52
    朏
    1.52
     lze
    1.52
    comune
    1.50
    Activations Density 0.014%

    No Known Activations