© 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. 11366
    Prev
    Next
    INDEX
    Explanations

    wikipedia list entries

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

    Wikipedia links

    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
     മനസ
    0.57
     ہوگئی
    0.53
     महत्वा
    0.52
    立
    0.51
    女
    0.50
    全新
    0.50
    全新的
    0.50
    वेळी
    0.49
    仔细
    0.49
     ребят
    0.49
    POSITIVE LOGITS
     Wikipedia
    0.85
     Wikimedia
    0.85
    Wikipedia
    0.82
    disamb
    0.80
    ː
    0.79
     disamb
    0.77
     /ˈ
    0.77
    ,[
    0.72
    wikipedia
    0.72
     [[
    0.72
    Activations Density 0.230%

    No Known Activations