© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47064
    Prev
    Next
    INDEX
    Explanations

    occupations and skilled trades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     psychotherapy
    -0.79
    Doctor
    -0.77
    談社
    -0.76
     gérer
    -0.75
     lawyers
    -0.75
     rowing
    -0.74
     businesswoman
    -0.73
     magistrate
    -0.72
    וֹ
    -0.72
     tutoring
    -0.71
    POSITIVE LOGITS
     electrician
    1.73
     mechanics
    1.55
     elect
    1.54
     Elect
    1.50
     maintenance
    1.45
     mechanic
    1.40
     electrical
    1.35
     carpenter
    1.34
     pipe
    1.31
     Maintenance
    1.30
    Activations Density 0.047%

    No Known Activations