© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 57032
    Prev
    Next
    INDEX
    Explanations

    acceptance of limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     матрицы
    0.54
    ibatkan
    0.52
    п
    0.52
     нарушение
    0.51
     ниж
    0.48
     mathematically
    0.48
     называется
    0.48
     немец
    0.47
     изображения
    0.46
     комплект
    0.46
    POSITIVE LOGITS
    饋
    0.47
    Infrastructure
    0.45
    claimer
    0.44
     构建
    0.44
    微软
    0.44
    sourcePort
    0.43
    视图
    0.43
     Carnegie
    0.43
    ശ്വാ
    0.43
     Island
    0.42
    Activations Density 0.001%

    No Known Activations