© 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. 40-GEMMASCOPE-2-RES-262K
    7. 130097
    Prev
    Next
    INDEX
    Explanations

    minified, fundamentally, String, Sovereign, demonstrating

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     منذ
    0.44
     効果
    0.43
     dna
    0.43
     ඔබේ
    0.42
     الحي
    0.42
     abordagem
    0.41
     県
    0.41
     nw
    0.40
    ذاء
    0.40
     abord
    0.40
    POSITIVE LOGITS
     included
    0.41
    implies
    0.41
     approving
    0.40
    ahan
    0.38
     preview
    0.38
    许可证
    0.38
     imply
    0.37
     unexpected
    0.37
     unsatisfactory
    0.37
     hint
    0.36
    Activations Density 0.002%

    No Known Activations