© 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. 117326
    Prev
    Next
    INDEX
    Explanations

    money amounts and currency

    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
     we
    -0.06
     Websites
    -0.06
     samples
    -0.06
    clubs
    -0.06
     websites
    -0.06
     एडिटिंग
    -0.06
     bonjour
    -0.06
     up
    -0.06
     inneh
    -0.06
     usamos
    -0.05
    POSITIVE LOGITS
     damals
    0.07
     당시
    0.07
     سے
    0.07
    那时候
    0.06
    当時
    0.06
    originally
    0.06
    оні
    0.06
    當時
    0.06
    当時の
    0.06
    ರಲ್ಲಿ
    0.06
    Activations Density 0.003%

    No Known Activations