© 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. 169923
    Prev
    Next
    INDEX
    Explanations

    Original Sin and dresses

    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
     yú
    0.40
     julio
    0.38
    phrine
    0.38
    持って
    0.38
     premio
    0.37
     ਤਾਂ
    0.37
    тельного
    0.37
    dcsset
    0.37
    ურად
    0.36
    軫
    0.36
    POSITIVE LOGITS
    рок
    0.49
     Teams
    0.42
     Cube
    0.42
     Tests
    0.42
    ปล
    0.42
     Opie
    0.40
     Discovery
    0.39
     ASP
    0.39
    لاه
    0.39
     Loose
    0.39
    Activations Density 0.000%

    No Known Activations