© 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. 117591
    Prev
    Next
    INDEX
    Explanations

    foreign corrupt practices act

    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
     inspired
    -0.07
     اینجا
    -0.06
     trabajan
    -0.06
    Here
    -0.06
     Aquí
    -0.06
     conflic
    -0.06
     inspiration
    -0.06
     চোখের
    -0.06
     brightly
    -0.06
     here
    -0.06
    POSITIVE LOGITS
     Surveillance
    0.07
     próxima
    0.06
     недель
    0.06
    iteta
    0.06
     ассо
    0.06
     drone
    0.05
     هفته
    0.05
     magnets
    0.05
     düzey
    0.05
     व्हाट्सएप
    0.05
    Activations Density 0.048%

    No Known Activations