© 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. 35838
    Prev
    Next
    INDEX
    Explanations

    got or gotcha

    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
    ä
    0.96
    ิง
    0.95
     that
    0.91
    ка
    0.91
    える
    0.88
    กว่า
    0.86
     decidió
    0.85
    ální
    0.84
    ções
    0.84
    क
    0.83
    POSITIVE LOGITS
    ל
    1.17
    你
    1.10
    ra
    1.09
    l
    1.07
    ্ট
    1.02
    n
    1.01
    rt
    0.97
    说是
    0.95
    $
    0.93
    re
    0.90
    Activations Density 0.004%

    No Known Activations