© 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. 8120
    Prev
    Next
    INDEX
    Explanations

    producing or yielding

    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
     myocytes
    1.86
    样子
    1.84
    f
    1.83
    ند
    1.80
    ak
    1.77
    giờ
    1.73
    ยายน
    1.73
    ктор
    1.73
     majd
    1.72
    proteins
    1.72
    POSITIVE LOGITS
    ер
    2.05
    Issledovatel
    2.02
    лло
    1.98
    𝗕
    1.85
    OS
    1.80
     polygon
    1.78
     symbol
    1.77
     giz
    1.75
    ل
    1.75
    ت
    1.75
    Activations Density 0.014%

    No Known Activations