© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94418
    Prev
    Next
    INDEX
    Explanations

    news, country, evening, clothing

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

    setup() function calls

    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
    Negative Logits
    勍
    0.52
    ilden
    0.47
    igheden
    0.46
    滤
    0.46
     परिचालन
    0.46
    运算符
    0.45
    咏
    0.45
    iedz
    0.45
    炜
    0.44
     критери
    0.44
    POSITIVE LOGITS
     on
    0.57
     bul
    0.55
    を
    0.54
     erat
    0.52
     bulging
    0.51
    に
    0.50
     with
    0.50
     of
    0.49
    HTML
    0.49
     mit
    0.49
    Activations Density 0.000%

    No Known Activations