© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9925
    Prev
    Next
    INDEX
    Explanations

    ampersand entity codes

    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
    ли
    2.17
    其
    1.78
    ત
    1.69
    うち
    1.63
    특별시
    1.59
    స్‌
    1.57
    うまく
    1.57
    ت
    1.52
    其他
    1.47
    い
    1.47
    POSITIVE LOGITS
    amp
    2.05
    ndash
    1.85
    an
    1.68
    as
    1.66
    mdash
    1.62
    nbsp
    1.59
    rsquo
    1.55
    rdquo
    1.52
    d
    1.52
     কিন্ত
    1.50
    Activations Density 0.018%

    No Known Activations