© 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. 123757
    Prev
    Next
    INDEX
    Explanations

    physical states and regulation

    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
    ي
    0.50
    ysław
    0.46
     treason
    0.45
    л
    0.45
     paced
    0.45
    人
    0.45
     mediated
    0.44
    ټر
    0.44
    probability
    0.44
    amore
    0.44
    POSITIVE LOGITS
     जहां
    0.44
     此
    0.44
     외국
    0.43
     쉽게
    0.43
     เหมาะ
    0.42
     phụ
    0.41
     孔
    0.41
     thoại
    0.41
     داخل
    0.41
    谠
    0.41
    Activations Density 0.002%

    No Known Activations