© 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. 6102
    Prev
    Next
    INDEX
    Explanations

    instructions for user

    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
    t
    0.94
    ヨーロッパ
    0.83
    לת
    0.80
     faci
    0.80
    usnya
    0.77
    köy
    0.77
    {"
    0.76
     液
    0.76
    侯
    0.76
    yty
    0.75
    POSITIVE LOGITS
    сы
    0.96
    ваме
    0.94
    ва
    0.93
    ных
    0.92
    শিপ
    0.86
     ничего
    0.84
    ၈
    0.83
    боль
    0.82
    ского
    0.81
     быть
    0.80
    Activations Density 0.006%

    No Known Activations