© 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. 83821
    Prev
    Next
    INDEX
    Explanations

    automated expense 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
    oudre
    -0.80
     للاسماء
    -0.78
    癬
    -0.74
    ография
    -0.73
    Measures
    -0.71
    予約
    -0.71
    ooplankton
    -0.69
    horizontalLayout
    -0.68
    注文
    -0.67
    anilla
    -0.67
    POSITIVE LOGITS
     reimbursement
    2.20
     expenses
    1.94
     expense
    1.88
     mileage
    1.80
     travel
    1.72
     reimbur
    1.66
     reimburse
    1.65
     reimbursed
    1.62
    expenses
    1.53
    Expense
    1.48
    Activations Density 0.017%

    No Known Activations