© 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-16K
    7. 4617
    Prev
    Next
    INDEX
    Explanations

    meals: breakfast, lunch, dinner

    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
    ב
    2.09
    ق
    2.03
    ydı
    1.90
    ständig
    1.84
    u
    1.78
    ным
    1.77
    jų
    1.77
    lst
    1.73
    cation
    1.71
    ник
    1.70
    POSITIVE LOGITS
    ้ย
    1.98
    มัน
    1.84
    щение
    1.79
    ท์
    1.77
     وبعد
    1.77
    ्य
    1.74
     руководи
    1.73
    ยังมี
    1.71
    ानी
    1.66
    𝐨
    1.64
    Activations Density 0.192%

    No Known Activations