© 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. 56750
    Prev
    Next
    INDEX
    Explanations

    's followed by common words

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

    detailed definitions or later elaboration

    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
    爱情
    0.46
    职务
    0.46
    يطان
    0.44
    出于
    0.42
    㤟
    0.41
     Liebe
    0.40
    Leer
    0.39
    <strong>
    0.39
    ант
    0.39
     подви
    0.39
    POSITIVE LOGITS
     glad
    0.45
     drugih
    0.45
     smashing
    0.45
    হইবে
    0.44
     oblik
    0.43
     odgov
    0.42
     representado
    0.42
    IllegalArgument
    0.42
     lucky
    0.42
    getenv
    0.42
    Activations Density 0.002%

    No Known Activations