© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7264
    Prev
    Next
    INDEX
    Explanations

    các ngôn ngữ và chủ đề khác nhau

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    aksud
    0.52
     DE
    0.52
    します
    0.50
    Д
    0.48
     Program
    0.47
    字段
    0.47
     +=
    0.46
    一组
    0.45
    DE
    0.45
    पता
    0.45
    POSITIVE LOGITS
    ต่างๆ
    0.70
    ដ៏
    0.68
     nào
    0.67
     المختلفة
    0.64
     extremamente
    0.64
     terbaru
    0.63
     متنوع
    0.62
     nightlife
    0.60
    ที่มี
    0.59
     thông
    0.59
    Activations Density 0.002%

    No Known Activations