© 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. 3791
    Prev
    Next
    INDEX
    Explanations

    golden orbit

    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
    Negative Logits
     నమోదు
    0.82
     அறிவியல்
    0.72
     можем
    0.71
     याबाबत
    0.71
     వివిధ
    0.70
     Pemerintah
    0.68
     уены
    0.67
     вода
    0.66
    ករណ៍
    0.66
    棪
    0.66
    POSITIVE LOGITS
     as
    0.85
     trois
    0.82
     avec
    0.79
     la
    0.79
     t
    0.77
     four
    0.76
     h
    0.73
     quatre
    0.72
     cinq
    0.72
     with
    0.71
    Activations Density 0.601%

    No Known Activations