© 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. 167651
    Prev
    Next
    INDEX
    Explanations

    predicting sentence completions

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

    words related to computer science and languages

    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
     perhaps
    0.50
    分子
    0.48
    perhaps
    0.47
    they
    0.45
    Type
    0.45
    心理
    0.43
    %
    0.42
    碍
    0.42
    Perhaps
    0.42
    of
    0.41
    POSITIVE LOGITS
     lông
    0.51
     tigris
    0.49
     Ávila
    0.48
     thorax
    0.48
     verbunden
    0.47
     elegante
    0.47
     lúc
    0.47
     valam
    0.47
     Profil
    0.46
     umbilical
    0.46
    Activations Density 0.000%

    No Known Activations