© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 27426
    Prev
    Next
    INDEX
    Explanations

    just by, or looking for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ма
    0.48
    ۳
    0.43
    ಿ
    0.43
     არ
    0.43
    ３
    0.42
     prz
    0.41
    in
    0.40
    ٹ
    0.40
    ૪
    0.40
     стиль
    0.40
    POSITIVE LOGITS
    Business
    0.48
    '";
    0.48
    قيقة
    0.46
     ازيكم
    0.45
     Businessman
    0.43
     Business
    0.43
     Уен
    0.43
     Kanye
    0.43
     hMut
    0.43
    虧
    0.43
    Activations Density 0.014%

    No Known Activations