© 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. 16-GEMMASCOPE-2-RES-262K
    7. 35699
    Prev
    Next
    INDEX
    Explanations

    jury verdict

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    و
    1.50
    d
    1.48
    os
    1.46
    t
    1.40
     it
    1.30
    ن
    1.27
    س
    1.23
    z
    1.20
    o
    1.17
    i
    1.16
    POSITIVE LOGITS
    ф
    0.93
     كانت
    0.92
     času
    0.88
    خدم
    0.87
     தாக்கு
    0.86
     كتاب
    0.86
    ៉
    0.86
     الدولية
    0.84
     любят
    0.84
     تك
    0.84
    Activations Density 0.000%

    No Known Activations