© 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-65K
    7. 3545
    Prev
    Next
    INDEX
    Explanations

    python code imports

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     is
    0.70
     of
    0.66
    是
    0.66
     =
    0.64
     on
    0.64
    は
    0.64
     של
    0.61
     của
    0.59
    IdleSync
    0.59
    ędzy
    0.57
    POSITIVE LOGITS
    ل
    0.64
    ୩
    0.61
     sigu
    0.56
    राधना
    0.55
     cuidad
    0.55
     boton
    0.55
     ambito
    0.54
     luta
    0.54
    чета
    0.53
    тта
    0.53
    Activations Density 0.145%

    No Known Activations