© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103475
    Prev
    Next
    INDEX
    Explanations

    payroll processing

    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
    ushu
    -0.81
     slump
    -0.75
    ougou
    -0.74
    :\/\/
    -0.74
    tü
    -0.74
     tü
    -0.73
    linewidth
    -0.71
    lü
    -0.71
     todas
    -0.70
    Diabetes
    -0.70
    POSITIVE LOGITS
     payroll
    5.28
     Payroll
    3.92
    payroll
    3.69
    Payroll
    3.63
     pay
    2.92
     paycheck
    2.58
     salary
    2.56
     pays
    2.33
     wage
    2.31
     wages
    2.28
    Activations Density 0.042%

    No Known Activations