© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 41888
    Prev
    Next
    INDEX
    Explanations

    entertainment business and industry

    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
    ו
    2.06
    ‌ای
    2.03
    nými
    1.66
    اً
    1.66
    ‌است
    1.63
    ד
    1.59
    itev
    1.58
     Ее
    1.55
    ‌ها
    1.49
    ină
    1.49
    POSITIVE LOGITS
    та
    1.77
    na
    1.63
    т
    1.58
    suffixes
    1.55
    tir
    1.50
     merece
    1.46
    ia
    1.45
    า
    1.45
    }\
    1.44
    ara
    1.44
    Activations Density 0.001%

    No Known Activations