© 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. 75947
    Prev
    Next
    INDEX
    Explanations

    various common words

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

    as elements, funny film, or common

    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
    Lisa
    0.51
     is
    0.49
    per
    0.48
    re
    0.47
    sche
    0.47
    親
    0.46
    un
    0.46
     happens
    0.46
    bors
    0.46
     beetles
    0.46
    POSITIVE LOGITS
    inggi
    0.50
     crescente
    0.50
    ۷
    0.49
    }<\
    0.49
    ործ
    0.49
    ͚
    0.48
    шая
    0.48
    titleTextStyle
    0.48
    емым
    0.47
     Oldborough
    0.47
    Activations Density 0.000%

    No Known Activations