© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2362
    Prev
    Next
    INDEX
    Explanations

    有所不同

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     bệnh
    0.32
     เอง
    0.31
     필수
    0.31
     linkCell
    0.31
     суд
    0.30
    링크
    0.30
    医师
    0.30
     Awareness
    0.30
     Linking
    0.30
    蜞
    0.30
    POSITIVE LOGITS
    了不少
    0.39
     craze
    0.39
    ul
    0.39
     viciss
    0.37
    is
    0.35
    pped
    0.35
    ud
    0.35
    burgo
    0.34
     sucesivamente
    0.33
     ferocious
    0.32
    Activations Density 0.015%

    No Known Activations