© 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. 28309
    Prev
    Next
    INDEX
    Explanations

    could include examples

    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
     основные
    0.46
     Полу
    0.44
     Можно
    0.43
    ’;
    0.43
    idhi
    0.42
    offsetTop
    0.42
     Согласно
    0.41
     удалось
    0.41
     основним
    0.40
     remains
    0.39
    POSITIVE LOGITS
    婚礼
    0.47
    洗
    0.46
     đình
    0.45
    例子
    0.45
     jakieś
    0.45
     свадь
    0.43
     mít
    0.43
     países
    0.43
     बॉबी
    0.42
     například
    0.42
    Activations Density 0.003%

    No Known Activations