© 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. 54303
    Prev
    Next
    INDEX
    Explanations

    chief financial officer

    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
     tích
    -0.75
    Cliente
    -0.72
     lô
    -0.70
    mqtt
    -0.69
    verly
    -0.69
    delser
    -0.68
    Breakfast
    -0.68
     TSH
    -0.68
     khảo
    -0.68
     presidencial
    -0.68
    POSITIVE LOGITS
     finance
    3.67
     Finance
    3.27
     accounting
    3.06
    Finance
    3.02
    finance
    2.98
     financial
    2.97
     Accounting
    2.64
     FINANCE
    2.55
     accountants
    2.52
     accountant
    2.50
    Activations Density 0.064%

    No Known Activations