Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 44514
    Prev
    Next
    INDEX
    Explanations

    knowledge graphs

    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
    EN
    1.85
    5
    1.48
    ES
    1.48
    2
    1.46
     Toutes
    1.43
    7
    1.43
     soumis
    1.39
    0
    1.38
    เมื่อ
    1.34
    EDS
    1.34
    POSITIVE LOGITS
    ا
    2.73
    a
    1.82
    o
    1.77
    tions
    1.74
    e
    1.69
    า
    1.69
    יות
    1.65
    t
    1.64
    া
    1.62
    y
    1.55
    Activations Density 0.000%

    No Known Activations