© 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. 176346
    Prev
    Next
    INDEX
    Explanations

    after entering

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

    lists of items, numbered lists, parenthetical statements

    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
     Änderung
    0.48
     personnal
    0.47
    caire
    0.46
    baren
    0.46
     Deutscher
    0.46
     fác
    0.45
    britannien
    0.45
    (
    0.45
     উল্লেখযোগ্য
    0.44
     προσωπ
    0.44
    POSITIVE LOGITS
     rigorously
    0.46
     vacío
    0.45
     độ
    0.44
    ნ
    0.44
     !!!!!
    0.43
    도를
    0.43
    েন্সি
    0.42
     لی
    0.42
     don
    0.42
     bubbly
    0.41
    Activations Density 0.000%

    No Known Activations