© 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. 85314
    Prev
    Next
    INDEX
    Explanations

    following words after out

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

    foreign language words

    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
    speeds
    0.41
     нами
    0.41
     FileInputStream
    0.41
    цени
    0.39
    се
    0.39
    我
    0.39
    分手
    0.38
    澤
    0.38
    脾
    0.38
     самые
    0.38
    POSITIVE LOGITS
    녔
    0.53
     rétréc
    0.52
     francês
    0.51
    nim
    0.50
     sprzedaży
    0.50
    ভূম
    0.50
     gud
    0.48
    Ꭲ
    0.48
    น์
    0.48
     pozwala
    0.47
    Activations Density 0.001%

    No Known Activations