© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 1517
    Prev
    Next
    INDEX
    Explanations

    pudendal nerve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ع
    1.70
    ور
    1.49
    как
    1.49
    і
    1.47
    א
    1.46
    ка
    1.45
    いた
    1.45
    ла
    1.44
    ที่มี
    1.44
    а
    1.38
    POSITIVE LOGITS
     havoc
    1.71
    y
    1.71
    不懂
    1.69
    RE
    1.67
    不一样
    1.66
    STE
    1.55
    岖
    1.54
     pleasure
    1.53
    こと
    1.52
    k
    1.52
    Activations Density 0.001%

    No Known Activations