© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 3513
    Prev
    Next
    INDEX
    Explanations

    receiving active

    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
     dotycz
    1.41
    ‌ی
    1.38
    ’
    1.34
    ings
    1.29
     картины
    1.25
     superconductors
    1.23
     scarring
    1.22
    霆
    1.20
     habido
    1.14
     prolifer
    1.09
    POSITIVE LOGITS
    ع
    1.91
    ส์
    1.73
    ly
    1.70
    redients
    1.56
    他
    1.52
    ת
    1.40
    주
    1.35
    onycha
    1.32
    the
    1.31
    ش
    1.30
    Activations Density 0.704%

    No Known Activations