© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8861
    Prev
    Next
    INDEX
    Explanations

    clothing size and fit

    np_acts-logits-general · gemini-2.5-flash-lite

    sizes and fit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     शक्त
    0.60
    熵
    0.57
     सत्ता
    0.48
     apopt
    0.48
    謗
    0.46
    텃
    0.46
    quorum
    0.46
    餌
    0.44
     amea
    0.44
    ত্য
    0.44
    POSITIVE LOGITS
     fit
    0.93
     Fit
    0.87
    フィット
    0.80
     fitting
    0.79
     サイズ
    0.79
     fitted
    0.79
    サイズ
    0.77
     unisex
    0.75
     Fitting
    0.74
     Fitted
    0.73
    Activations Density 0.152%

    No Known Activations