© 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. 249566
    Prev
    Next
    INDEX
    Explanations

    non-English characters

    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
     فلسطینی
    0.54
    ந்துள்ளது
    0.51
    unprocessable
    0.50
    findall
    0.49
    کرات
    0.49
    ueto
    0.48
    ;"+
    0.47
    newL
    0.47
    ʒ
    0.46
    ;',
    0.46
    POSITIVE LOGITS
     دليل
    0.45
    的這個
    0.42
     WHIT
    0.42
    та
    0.41
     تت
    0.41
     ಧ
    0.41
     WOR
    0.40
    يد
    0.40
     伊
    0.40
    鲍
    0.39
    Activations Density 0.001%

    No Known Activations