© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74808
    Prev
    Next
    INDEX
    Explanations

    safety and security regulations

    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
    Negative Logits
    бор
    0.49
    Боль
    0.47
    פון
    0.46
    hilt
    0.46
    У
    0.46
    合适的
    0.45
    电脑
    0.45
     aho
    0.44
    氨
    0.44
    الصفحه
    0.44
    POSITIVE LOGITS
     χαρακτη
    0.40
    ewana
    0.40
    の特徴
    0.39
     معی
    0.39
     पहुँचा
    0.38
     pathogenesis
    0.38
     ਭ
    0.38
     чувства
    0.38
    MediaType
    0.37
     প্রকাশের
    0.37
    Activations Density 0.002%

    No Known Activations