© 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. 108693
    Prev
    Next
    INDEX
    Explanations

    Nepal heard, chicken noodle, pork belly, graphics card

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

    questions about life choices or access

    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
     Pages
    0.48
     This
    0.47
     to
    0.46
     de
    0.45
    This
    0.45
     Maver
    0.44
    2
    0.44
     Those
    0.44
    0
    0.44
     sepat
    0.43
    POSITIVE LOGITS
    например
    0.51
    шымта
    0.47
    நீ
    0.47
    лён
    0.46
     координатами
    0.46
    pannt
    0.46
    ंबी
    0.45
    घड
    0.45
    épaisseur
    0.45
     пан
    0.45
    Activations Density 0.001%

    No Known Activations