© 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-65K
    7. 1660
    Prev
    Next
    INDEX
    Explanations

    work and busy periods

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     phosph
    0.44
    引导
    0.42
     sophisticated
    0.42
     polymorphism
    0.41
     registers
    0.40
     sophistication
    0.40
     topological
    0.40
     convolutional
    0.39
     \
    0.38
    amsmath
    0.37
    POSITIVE LOGITS
     workday
    1.45
     workload
    1.36
     trabajo
    1.28
     trabalho
    1.27
     work
    1.27
     hours
    1.23
     ജോലി
    1.22
    工作
    1.20
     ساعات
    1.16
     lavoro
    1.16
    Activations Density 0.568%

    No Known Activations