© 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. 25255
    Prev
    Next
    INDEX
    Explanations

    core concepts and operations

    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
    特点
    0.50
     dialed
    0.49
    人
    0.45
    人群
    0.44
    这时
    0.43
    Veh
    0.43
    伫
    0.42
    тор
    0.42
    瞬间
    0.41
    可以直接
    0.41
    POSITIVE LOGITS
    qh
    0.43
     захворю
    0.42
    .[
    0.41
     financières
    0.41
    ր
    0.41
     adding
    0.40
    નું
    0.40
     induces
    0.40
    т
    0.40
     благо
    0.40
    Activations Density 0.000%

    No Known Activations