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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73147
    Prev
    Next
    INDEX
    Explanations

    medical billing and payments

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases related to payment methods and financial transactions, especially credit cards, billing, and tax-deductible items.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    が悪
    -1.25
     in
    -1.22
    だが
    -1.13
    áss
    -1.13
    ///</
    -1.12
     enrique
    -1.09
     BitSet
    -1.09
    
    -1.08
    ohol
    -1.08
     pedimos
    -1.07
    POSITIVE LOGITS
     récemment
    1.23
    another
    1.22
    without
    1.09
     Spon
    1.07
     おしゃれ
    1.06
     presentato
    1.03
     fortement
    1.03
     innymi
    1.02
     martie
    1.02
    บาย
    1.01
    Activations Density 0.072%

    No Known Activations