© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6820
    Prev
    Next
    INDEX
    Explanations

    the present invention relates to

    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
    浱
    0.64
    结局
    0.61
    脤
    0.61
     سیاسی
    0.57
    上涨
    0.57
    赈
    0.56
    丵
    0.55
    abhavam
    0.54
    摈
    0.54
    acariy
    0.53
    POSITIVE LOGITS
     invention
    0.98
     embodiments
    0.83
    invention
    0.79
     inventions
    0.79
     inventors
    0.77
    本発明
    0.77
     изобре
    0.77
     patent
    0.76
     inventive
    0.69
     novel
    0.63
    Activations Density 0.006%

    No Known Activations