© 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. 19170
    Prev
    Next
    INDEX
    Explanations

    today's topics and announcements

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

    introducing today's topic

    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
    不斷
    0.43
     každ
    0.43
    人間
    0.40
    不断
    0.39
    ヴ
    0.39
     каждый
    0.39
    汇总
    0.39
     ഓരോ
    0.39
    unca
    0.39
    各
    0.39
    POSITIVE LOGITS
     topic
    0.59
     Topic
    0.57
     tenemos
    0.56
     موضوع
    0.54
     theme
    0.54
    Topic
    0.53
     we
    0.52
     Thema
    0.52
     Theme
    0.51
     spéciales
    0.50
    Activations Density 0.046%

    No Known Activations