© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10890
    Prev
    Next
    INDEX
    Explanations

    bmp and programme

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_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
    s
    3.39
    t
    2.55
    re
    2.06
    sm
    2.06
    ς
    2.03
    siz
    1.95
    ים
    1.88
    sy
    1.88
    sz
    1.86
    srv
    1.84
    POSITIVE LOGITS
    ಾ
    1.87
    ა
    1.71
    がいる
    1.70
    طور
    1.55
    ливо
    1.53
    зирован
    1.53
    но
    1.52
    มัน
    1.52
    đer
    1.50
    chließlich
    1.49
    Activations Density 0.002%

    No Known Activations