© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211688
    Prev
    Next
    INDEX
    Explanations

    foreign words and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite

    medical examination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    कोल
    0.49
     Episcopal
    0.46
    Α
    0.46
     sprawling
    0.45
    트롤
    0.44
    א
    0.44
     수
    0.44
     Promenade
    0.44
     Collider
    0.43
    Ա
    0.43
    POSITIVE LOGITS
    rj
    0.49
     advices
    0.47
    sys
    0.46
     окна
    0.46
    卵
    0.45
    .';
    0.45
     ventric
    0.45
     камеры
    0.44
     cárc
    0.43
    膀
    0.43
    Activations Density 0.001%

    No Known Activations