© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116740
    Prev
    Next
    INDEX
    Explanations

    wages, salary, pay, and hourly rates

    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
    Not in Any Lists

    No Comments

    Negative Logits
     leta
    -0.82
    RUnlock
    -0.77
    StatusBadRequest
    -0.75
    ){$\
    -0.73
     Rockwell
    -0.71
    ReferenceEquals
    -0.70
     dio
    -0.69
     Rostock
    -0.69
    unknownFields
    -0.68
     gema
    -0.68
    POSITIVE LOGITS
     wages
    5.28
     wage
    4.03
     Wages
    3.52
    wage
    2.83
     Wage
    2.69
    Wage
    2.67
     salaries
    2.33
     salary
    2.28
     hourly
    2.23
     pay
    2.22
    Activations Density 0.024%

    No Known Activations