© 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. 9466
    Prev
    Next
    INDEX
    Explanations

    lists conjunctions and descriptors

    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
    ва
    1.36
    ン
    1.36
    り
    1.36
    ال
    1.34
    ა
    1.34
    ي
    1.33
    ت
    1.32
    ம்
    1.31
     сообщает
    1.29
     Қ
    1.27
    POSITIVE LOGITS
    ↵
    1.18
    side
    1.11
     hardcore
    1.11
    techn
    1.05
    ‌ترین
    1.05
    ters
    1.03
    terr
    1.02
    sw
    1.00
    shot
    0.96
     halogen
    0.95
    Activations Density 0.651%

    No Known Activations