© 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. 30253
    Prev
    Next
    INDEX
    Explanations

    online marketplace

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

    describing purpose or intent

    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
    Not in Any Lists

    No Comments

    Negative Logits
    <unused2018>
    0.56
    зму
    0.51
     સલા
    0.51
    タル
    0.50
     ち
    0.50
     ജ
    0.50
    жами
    0.50
     禁止
    0.49
     武田
    0.49
    の後
    0.49
    POSITIVE LOGITS
    to
    0.62
     a
    0.55
    äs
    0.54
     as
    0.52
    ikk
    0.49
    ne
    0.49
    inda
    0.49
    ina
    0.48
     package
    0.47
    itta
    0.47
    Activations Density 0.000%

    No Known Activations