© 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. 109478
    Prev
    Next
    INDEX
    Explanations

    syntax: `::` or `**`

    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
    步驟
    0.45
    ت
    0.45
    快速
    0.44
    ب
    0.44
    ви
    0.44
    bine
    0.43
    ขั้น
    0.43
    c
    0.42
    إذا
    0.42
    の手
    0.41
    POSITIVE LOGITS
    یثیت
    0.50
    Hugo
    0.48
    reszt
    0.46
    rolled
    0.45
    블릿
    0.45
    EDS
    0.45
    Storia
    0.45
    ᱽ
    0.44
    wohner
    0.44
    :],
    0.44
    Activations Density 0.001%

    No Known Activations