© 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. 892
    Prev
    Next
    INDEX
    Explanations

    UPI, EMI, ₀

    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
    可以
    1.84
    此
    1.45
     gelungen
    1.40
     малень
    1.38
    清理
    1.36
     ermöglicht
    1.34
    걸
    1.34
     kleines
    1.29
    がありますが
    1.29
    ва
    1.27
    POSITIVE LOGITS
    ς
    1.60
    ات
    1.50
    ের
    1.45
    smanship
    1.45
    ן
    1.44
    s
    1.35
     CAGR
    1.31
    нтэр
    1.29
    тов
    1.26
    ין
    1.23
    Activations Density 0.005%

    No Known Activations