© 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-16K
    7. 14717
    Prev
    Next
    INDEX
    Explanations

    turn

    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_16k_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
    ı
    2.09
     DMSO
    1.97
    our
    1.94
    ا
    1.94
    ant
    1.93
    lah
    1.88
    ening
    1.85
    car
    1.84
    aży
    1.84
     forn
    1.82
    POSITIVE LOGITS
    ੫
    1.97
     wrenches
    1.95
    ઓ
    1.90
     dioxide
    1.77
    している
    1.71
     conhecer
    1.70
     кстати
    1.69
     dusky
    1.69
    色彩
    1.68
    تام
    1.66
    Activations Density 0.058%

    No Known Activations