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

    Neuronpedia

    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. 43808
    Prev
    Next
    INDEX
    Explanations

    RAINN telephone number/website

    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
    д
    1.77
    і
    1.71
    т
    1.63
    ic
    1.51
    ot
    1.45
    ac
    1.35
    лки
    1.33
     такі
    1.31
    о
    1.30
    е
    1.30
    POSITIVE LOGITS
    e
    1.87
    a
    1.80
    cito
    1.43
    ‌ای
    1.40
    brides
    1.40
    ی
    1.37
     Dari
    1.31
     Brows
    1.29
     Spes
    1.28
    course
    1.27
    Activations Density 0.002%

    No Known Activations