© 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. 235351
    Prev
    Next
    INDEX
    Explanations

    non-English words or characters

    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
     StatefulWidget
    0.46
    EM
    0.46
    ोगी
    0.46
    OV
    0.45
    특별시
    0.44
     COMPANY
    0.44
     tenders
    0.42
    ñ
    0.42
     স্থ
    0.42
    ेंगी
    0.41
    POSITIVE LOGITS
    Institut
    0.47
    ăz
    0.46
     matemáticas
    0.45
    Après
    0.45
     años
    0.45
    轢
    0.44
    脓
    0.44
    䒿
    0.44
    ।’
    0.44
    Setelah
    0.44
    Activations Density 0.000%

    No Known Activations