© 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-16K
    7. 12504
    Prev
    Next
    INDEX
    Explanations

    assessing proficiency

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     seen
    0.37
    avourable
    0.37
    ਈ
    0.36
    ަމ
    0.36
    %',
    0.35
     Informatics
    0.35
     achievable
    0.34
    ResponseType
    0.34
    ieur
    0.34
     Seen
    0.34
    POSITIVE LOGITS
     adept
    1.13
    擅
    1.08
     proficient
    1.04
     excels
    1.00
     giỏi
    0.96
     excel
    0.95
     excelente
    0.82
     excelled
    0.80
    excellent
    0.80
     эффективно
    0.80
    Activations Density 0.413%

    No Known Activations