© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129612
    Prev
    Next
    INDEX
    Explanations

    financial transactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     både
    -0.06
     levando
    -0.06
     où
    -0.06
     Clothing
    -0.06
     بناء
    -0.06
     costruzione
    -0.06
     eateries
    -0.06
     inclusivity
    -0.06
     inkl
    -0.06
     alimento
    -0.06
    POSITIVE LOGITS
     financial
    0.07
    financial
    0.07
     financieros
    0.07
     শাস্ত্র
    0.07
     transaction
    0.06
     Exchequer
    0.06
     финансовых
    0.06
     keuangan
    0.06
    金融
    0.06
    🐡
    0.06
    Activations Density 0.001%

    No Known Activations