© 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. 226723
    Prev
    Next
    INDEX
    Explanations

    create understanding

    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
     mencionar
    0.54
    陌
    0.53
    филь
    0.52
    ем
    0.52
     всё
    0.51
    湄
    0.50
    рия
    0.50
     интерес
    0.50
    ев
    0.49
    urias
    0.49
    POSITIVE LOGITS
    ;
    0.48
    ază
    0.47
     artists
    0.45
    ches
    0.45
    jar
    0.45
    Silver
    0.45
     recoup
    0.44
    covers
    0.44
    ch
    0.44
    PERS
    0.43
    Activations Density 0.000%

    No Known Activations