© 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. 144247
    Prev
    Next
    INDEX
    Explanations

    where... there

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

    last knowledge update

    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
    )。
    0.51
     hide
    0.49
     þe
    0.48
     Kiya
    0.48
     soci
    0.46
    使用
    0.45
     shi
    0.45
    ↵
    0.44
     synt
    0.44
     hides
    0.43
    POSITIVE LOGITS
    asile
    0.54
    ዦ
    0.51
    ಸು
    0.50
     зон
    0.49
     улице
    0.48
    aso
    0.45
    isteria
    0.45
    iri
    0.45
     вечером
    0.45
    สุขภาพ
    0.45
    Activations Density 0.002%

    No Known Activations