© 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. 2680
    Prev
    Next
    INDEX
    Explanations

    award, globe, reference, reels

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

    symbols and multilingual content

    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
    f
    0.60
    dollars
    0.55
     Dollars
    0.54
     dollars
    0.49
    contexts
    0.48
    <h3>
    0.45
    Dollars
    0.44
     complementary
    0.44
    ++
    0.44
    <h6>
    0.43
    POSITIVE LOGITS
     başar
    0.54
     ฮ
    0.53
     gewährleisten
    0.52
     আশঙ্কা
    0.50
     മാലി
    0.50
     सेमीफाइनल
    0.49
     ﺍ
    0.48
     ব্র
    0.48
     ถาม
    0.47
     सुनिश्चित
    0.47
    Activations Density 0.000%

    No Known Activations