© 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. 89651
    Prev
    Next
    INDEX
    Explanations

    universities and higher education

    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
     配
    0.38
     식
    0.37
     Style
    0.36
     로
    0.35
     Collection
    0.35
     式
    0.34
     Credits
    0.34
     عمل
    0.34
    式
    0.34
     رو
    0.33
    POSITIVE LOGITS
    enroll
    0.39
     बेरोज
    0.39
     sectional
    0.38
    ından
    0.38
     Wash
    0.38
    iorari
    0.36
     fielded
    0.36
     pouls
    0.36
     vigente
    0.35
     universitario
    0.35
    Activations Density 0.002%

    No Known Activations