© 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. 127805
    Prev
    Next
    INDEX
    Explanations

    court cases v

    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
    .
    -1.34
     zoude
    -1.32
    幛
    -1.29
    𓁹
    -1.23
     $^{\
    -1.22
    macam
    -1.21
     vorsichtig
    -1.21
     kvalitet
    -1.21
    mediately
    -1.20
    </h4>
    -1.20
    POSITIVE LOGITS
     or
    1.33
     it
    1.27
     While
    1.09
     using
    1.09
    (")");
    1.07
    Lá
    1.05
    Lí
    1.05
     At
    1.05
    спользова
    1.04
     many
    1.02
    Activations Density 0.020%

    No Known Activations