© 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. 128386
    Prev
    Next
    INDEX
    Explanations

    time it takes

    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
    zembro
    -1.80
    </b>
    -1.70
     プレミアム
    -1.66
     macetas
    -1.65
    ฀
    -1.63
    ໑
    -1.59
    很多的
    -1.56
    衪
    -1.54
     zugelassen
    -1.54
     jLabel
    -1.54
    POSITIVE LOGITS
     While
    1.76
     Its
    1.67
     these
    1.67
    ANIEL
    1.66
     Interestingly
    1.66
     These
    1.62
    gemeen
    1.61
     Not
    1.57
     Obviously
    1.57
     Hopefully
    1.54
    Activations Density 0.009%

    No Known Activations