© 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. 248872
    Prev
    Next
    INDEX
    Explanations

    security and information

    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
     கா
    0.50
     พัน
    0.47
     אַ
    0.46
     in
    0.45
     का
    0.45
     ที่
    0.44
    ：
    0.44
     ETH
    0.43
    ้า
    0.43
     CP
    0.43
    POSITIVE LOGITS
    ઉન
    0.54
     বাড়তে
    0.54
    સભા
    0.52
     superiori
    0.47
    чить
    0.47
    )>\
    0.47
    гация
    0.47
    личе
    0.46
    لین
    0.46
     supérieurs
    0.46
    Activations Density 0.000%

    No Known Activations