© 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-16K
    7. 13624
    Prev
    Next
    INDEX
    Explanations

    infection

    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
    ו
    2.58
    ت
    2.11
    ত্ব
    1.99
    ח
    1.86
    ီ
    1.81
    로
    1.76
    一阵
    1.68
    ின
    1.67
    ны
    1.62
    很多的
    1.59
    POSITIVE LOGITS
    م
    2.91
    ate
    2.22
    m
    2.17
    rifice
    2.09
    day
    2.05
    ようになる
    1.94
    ai
    1.85
    net
    1.84
    zeit
    1.84
    り
    1.83
    Activations Density 0.034%

    No Known Activations