© 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-262K
    7. 43937
    Prev
    Next
    INDEX
    Explanations

    surprisingly + notable qualities

    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
    데
    2.06
    하여
    1.88
    là
    1.84
    ช่วง
    1.82
    ding
    1.73
    个
    1.72
    得知
    1.70
    自己
    1.67
    𝑭
    1.67
    不久
    1.65
    POSITIVE LOGITS
    с
    2.30
    го
    2.05
    ن
    1.58
    ли
    1.57
    लिंग
    1.44
     وعلى
    1.44
    е
    1.44
    логия
    1.43
    ーション
    1.41
    േ
    1.38
    Activations Density 0.010%

    No Known Activations