© 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. 128555
    Prev
    Next
    INDEX
    Explanations

    high quality or performance

    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
     by
    -1.55
     knew
    -1.53
    обзор
    -1.52
     when
    -1.48
     about
    -1.48
    Isso
    -1.45
     have
    -1.43
    嚳
    -1.41
    숯
    -1.40
     paž
    -1.39
    POSITIVE LOGITS
    </h5>
    1.65
     and
    1.63
    ');
    1.56
    蓠
    1.48
     dispuestos
    1.47
     \&
    1.41
    RunAsync
    1.38
    re
    1.38
    </b>
    1.34
    ١
    1.34
    Activations Density 0.060%

    No Known Activations