© 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. 145390
    Prev
    Next
    INDEX
    Explanations

    order of the universe

    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
    o
    1.02
    ו
    0.87
    و
    0.85
    ное
    0.84
    ኗ
    0.79
    ка
    0.78
    a
    0.73
    an
    0.72
    ı
    0.68
     \
    0.66
    POSITIVE LOGITS
    ación
    0.75
    ก
    0.69
     Optim
    0.59
    issä
    0.58
    торой
    0.57
     Rays
    0.56
     autres
    0.56
    ais
    0.55
     أب
    0.55
     Springsteen
    0.55
    Activations Density 0.002%

    No Known Activations