© 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. 35726
    Prev
    Next
    INDEX
    Explanations

    coriander leaves, powder, seeds

    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
    0.93
    ian
    0.77
    -
    0.70
    ↵↵
    0.69
    sch
    0.67
    ↵↵↵
    0.64
    owns
    0.63
    ↵↵↵↵
    0.62
    </strong>
    0.56
     ஈடுப
    0.56
    POSITIVE LOGITS
     Coelho
    0.71
    ä
    0.71
    cosine
    0.71
     bảy
    0.70
     cáo
    0.70
     QSOs
    0.70
     giọng
    0.69
    _
    0.68
    ۰
    0.68
    ۲
    0.68
    Activations Density 0.001%

    No Known Activations