© 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. 75756
    Prev
    Next
    INDEX
    Explanations

    X followed by Y

    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
    '/>
    0.42
    】
    0.40
    :)
    0.39
    )=
    0.38
    有两种
    0.37
     Introduction
    0.36
     ট্রান্স
    0.36
    ',)
    0.36
     Res
    0.35
     Founding
    0.35
    POSITIVE LOGITS
    все
    0.51
    ど
    0.51
    または
    0.50
     все
    0.49
    possibly
    0.47
     ну
    0.47
    щення
    0.47
    круг
    0.46
    not
    0.46
     практически
    0.46
    Activations Density 0.050%

    No Known Activations