© 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-65K
    7. 36365
    Prev
    Next
    INDEX
    Explanations

    automatically execute and enforce contracts

    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_65k_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
    Мы
    0.60
     نتی
    0.59
    И
    0.54
    Что
    0.52
    Из
    0.52
    Ди
    0.51
    П
    0.51
    Чтобы
    0.50
    Кто
    0.50
    По
    0.49
    POSITIVE LOGITS
     chow
    0.52
    mph
    0.49
     Midtown
    0.47
     almond
    0.47
     品
    0.46
     loafers
    0.46
    akespeare
    0.45
    oland
    0.45
     shillings
    0.45
     frances
    0.45
    Activations Density 0.002%

    No Known Activations