© 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. 128474
    Prev
    Next
    INDEX
    Explanations

    pairing food and wine

    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
     Endangered
    -0.06
     khawatir
    -0.06
    amb
    -0.06
     Thế
    -0.06
    руд
    -0.06
    点は
    -0.06
     IPO
    -0.05
     विधाय
    -0.05
     associ
    -0.05
    按照
    -0.05
    POSITIVE LOGITS
     such
    0.07
     nicht
    0.06
    深夜
    0.06
     szczegól
    0.06
     പ്രത്യേക
    0.06
    such
    0.06
     ရက်
    0.06
     inflict
    0.06
     thofe
    0.06
     घड़ी
    0.06
    Activations Density 0.002%

    No Known Activations