© 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. 216151
    Prev
    Next
    INDEX
    Explanations

    board games, informed choices

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

    salary estimates

    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
    ።
    0.57
    ActionMode
    0.49
    Sham
    0.48
    Pars
    0.44
    ۔
    0.44
    leyici
    0.43
     декора
    0.43
    UIAlert
    0.43
     Итак
    0.43
    Decoration
    0.42
    POSITIVE LOGITS
    [,
    0.53
    りん
    0.49
     contested
    0.48
    _,
    0.47
    *,
    0.47
     skirts
    0.47
     tents
    0.46
    __,
    0.45
     berths
    0.45
     lawyers
    0.45
    Activations Density 0.001%

    No Known Activations