© 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. 74801
    Prev
    Next
    INDEX
    Explanations

    array manipulation code snippets

    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
    یز
    0.45
     ग्रीन
    0.44
    Alan
    0.44
    Jason
    0.43
    leen
    0.43
    ⵄ
    0.42
     विलियम
    0.42
    Gotham
    0.41
    ˀ
    0.41
     儿童
    0.41
    POSITIVE LOGITS
     Maharashtra
    0.63
     Andhra
    0.62
     Maruti
    0.61
     bollywood
    0.60
     saree
    0.59
     Bollywood
    0.59
    Maharashtra
    0.57
     india
    0.55
     Kerala
    0.54
     Telangana
    0.54
    Activations Density 0.220%

    No Known Activations