© 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. 111640
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    technical or descriptive terms

    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
     পরই
    0.45
     Suche
    0.44
    元気
    0.43
    ပြော
    0.42
    鍵
    0.42
     Saya
    0.41
    V
    0.41
     Sø
    0.40
    手続き
    0.40
     instaur
    0.40
    POSITIVE LOGITS
    轱
    0.52
    жие
    0.51
    чы
    0.50
     राजांनी
    0.46
    ne
    0.46
    ни
    0.46
     разных
    0.46
    но
    0.45
    jezd
    0.45
     такое
    0.45
    Activations Density 0.001%

    No Known Activations