© 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-65K
    7. 28999
    Prev
    Next
    INDEX
    Explanations

    clever technique or static charts

    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_65k_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
    缘
    0.44
    唢
    0.43
    所有的
    0.43
    炀
    0.43
    亚
    0.41
     রহমান
    0.38
    摷
    0.38
     অত্য
    0.38
    赟
    0.38
    ጋገብ
    0.38
    POSITIVE LOGITS
    ’
    0.51
     violators
    0.47
    ’;
    0.43
     mereka
    0.42
    ’-
    0.42
    ’.
    0.41
     muertos
    0.40
    waukee
    0.40
     закон
    0.39
    stanbul
    0.39
    Activations Density 0.049%

    No Known Activations