© 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. 10750
    Prev
    Next
    INDEX
    Explanations

    math questions

    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
     for
    0.61
    ü
    0.54
    り
    0.54
    $
    0.50
    溱
    0.49
    不
    0.48
    ва
    0.47
     Debido
    0.47
    ב
    0.47
     with
    0.47
    POSITIVE LOGITS
    ко
    0.72
     взя
    0.63
     заяви
    0.62
    ﺷ
    0.59
     постро
    0.58
     сообщи
    0.58
    ши
    0.56
    нг
    0.55
    ல்
    0.55
     написа
    0.54
    Activations Density 0.137%

    No Known Activations