© 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. 31-GEMMASCOPE-2-RES-262K
    7. 71159
    Prev
    Next
    INDEX
    Explanations

    predictive insights

    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_31_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
     doctrina
    0.48
     política
    0.48
     доку
    0.46
     ши
    0.45
     document
    0.44
     dokument
    0.44
     법
    0.44
     Battles
    0.43
     tagline
    0.42
     OFFICIAL
    0.42
    POSITIVE LOGITS
    $^{
    0.50
    anskje
    0.47
     Veranstaltungen
    0.46
    astore
    0.46
    पणा
    0.45
    że
    0.45
    ছোট
    0.45
    zzo
    0.44
    মূলক
    0.43
    kal
    0.43
    Activations Density 0.003%

    No Known Activations