© 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. 121039
    Prev
    Next
    INDEX
    Explanations

    clothing and style descriptions

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

    Google DeepMind

    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
    бре
    0.45
    6
    0.44
    ،
    0.44
    雅黑
    0.44
    trunc
    0.43
    步驟
    0.43
     corporates
    0.43
    %';
    0.43
    ი
    0.43
    ѐ
    0.43
    POSITIVE LOGITS
     겨
    0.45
     Conversations
    0.45
     lao
    0.45
    ọi
    0.44
     ഫോ
    0.44
     nhận
    0.43
     По
    0.43
     เครื่อง
    0.43
     cang
    0.43
     വെ
    0.42
    Activations Density 0.003%

    No Known Activations