© 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. 56346
    Prev
    Next
    INDEX
    Explanations

    through too much

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

    rather than, to improve, USAP

    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
     দিল্লিতে
    0.46
    aqu
    0.43
     કોઈ
    0.43
    villa
    0.43
    ’!
    0.42
    ation
    0.42
    gäng
    0.41
     !}
    0.41
    urando
    0.41
    ’
    0.41
    POSITIVE LOGITS
     ogr
    0.52
     brz
    0.49
     topl
    0.49
     awal
    0.48
     streng
    0.47
     sqrt
    0.47
     masuk
    0.47
    ل
    0.46
    पाट
    0.46
     masy
    0.45
    Activations Density 0.000%

    No Known Activations