© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4711
    Prev
    Next
    INDEX
    Explanations

    reflects that

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    マンション
    0.46
    ဆက်
    0.45
    ٹوں
    0.43
    astically
    0.43
    <unused43>
    0.43
    ﺭ
    0.43
    牘
    0.43
    플
    0.42
    Pension
    0.42
    <unused85>
    0.42
    POSITIVE LOGITS
     воро
    0.61
    ى
    0.55
    a
    0.54
     گا
    0.49
     сверх
    0.48
     NSMutableArray
    0.48
     viewer
    0.47
     करावे
    0.47
    केल
    0.46
     \
    0.46
    Activations Density 0.000%

    No Known Activations