© 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. 126883
    Prev
    Next
    INDEX
    Explanations

    explaining definitions

    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
    推荐
    0.44
    ются
    0.42
    Program
    0.42
    Which
    0.41
    ственных
    0.41
    信息
    0.40
    QA
    0.40
    ⺝
    0.40
    给定
    0.40
    窥
    0.39
    POSITIVE LOGITS
     jauh
    0.45
     paraphernalia
    0.45
     shamb
    0.42
     oorlog
    0.42
     ruim
    0.42
     ilk
    0.41
    issime
    0.41
    otesi
    0.41
     těž
    0.41
     تجرب
    0.41
    Activations Density 0.002%

    No Known Activations