© 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. 130279
    Prev
    Next
    INDEX
    Explanations

    medicine and health topics

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

    cherish every moment

    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
    xFF
    0.54
     ISBN
    0.49
     kunna
    0.46
     hinsichtlich
    0.46
     THAT
    0.44
    บค้น
    0.44
     BEING
    0.44
     yh
    0.43
     ③
    0.43
     quilt
    0.43
    POSITIVE LOGITS
    arı
    0.49
     posao
    0.45
    glas
    0.44
    rato
    0.44
     retom
    0.44
    ellan
    0.43
    ladı
    0.43
     sezon
    0.43
    aur
    0.43
    nid
    0.42
    Activations Density 0.001%

    No Known Activations