© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15948
    Prev
    Next
    INDEX
    Explanations

    star ratings and scores

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

    rating or stars

    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
     officielles
    0.45
    ắn
    0.45
    僳
    0.44
     રાખો
    0.44
     awalnya
    0.43
     बोलो
    0.42
     наблю
    0.42
     uffic
    0.42
     কাদ
    0.42
    ાર્થી
    0.41
    POSITIVE LOGITS
    rating
    0.60
    Rated
    0.54
    ratings
    0.51
     rating
    0.51
     rated
    0.51
     Rated
    0.50
    ⭐⭐
    0.50
    rated
    0.49
    Rating
    0.49
     रेटिंग
    0.49
    Activations Density 0.015%

    No Known Activations