© 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. 98394
    Prev
    Next
    INDEX
    Explanations

    mortgage loans, FHA financing, student loans, NPA

    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
    턱
    -0.81
    缴
    -0.79
    harvest
    -0.76
    ኩ
    -0.75
    suporte
    -0.73
    filled
    -0.73
    悯
    -0.69
     knapp
    -0.69
    obrá
    -0.69
    コミュニケーション
    -0.68
    POSITIVE LOGITS
     loans
    4.59
     loan
    4.13
     Loans
    2.95
    loans
    2.88
    Loans
    2.75
     Loan
    2.67
    loan
    2.63
    Loan
    2.61
    贷款
    2.53
     LOAN
    2.23
    Activations Density 0.031%

    No Known Activations