© 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. 42916
    Prev
    Next
    INDEX
    Explanations

    nowadays foreign words and specific items

    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
    报告
    0.52
    鳕
    0.52
    纽约
    0.50
    设计
    0.50
     לק
    0.50
    诊断
    0.49
     decarbon
    0.48
    旨在
    0.48
    涵盖
    0.48
    肄
    0.47
    POSITIVE LOGITS
     nowadays
    0.50
     sams
    0.50
     salwar
    0.48
     rakh
    0.48
    Nowadays
    0.47
     Kabul
    0.46
     manusia
    0.44
    ありますが
    0.44
     wala
    0.43
     Nowadays
    0.43
    Activations Density 0.001%

    No Known Activations