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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3171
    Prev
    Next
    INDEX
    Explanations

    Academy names and AliExpress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ہوگ
    0.63
    то
    0.63
     Connecticut
    0.62
     AppBsky
    0.59
     Wisconsin
    0.57
     Kentucky
    0.57
     चळ
    0.57
    侢
    0.55
     playGame
    0.55
     Zoo
    0.54
    POSITIVE LOGITS
    name
    0.73
    ON
    0.63
    О
    0.62
    Soviet
    0.62
    rus
    0.61
    lang
    0.61
    Located
    0.60
    use
    0.59
    most
    0.59
    Name
    0.57
    Activations Density 0.002%

    No Known Activations