© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118778
    Prev
    Next
    INDEX
    Explanations

    Jean-Marc Ayrault

    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
    河南
    -0.07
     extracting
    -0.06
     Hannover
    -0.06
     destinados
    -0.06
     ምን
    -0.06
     множество
    -0.06
     prudent
    -0.06
     destinado
    -0.06
     ait
    -0.05
     termed
    -0.05
    POSITIVE LOGITS
     légales
    0.06
     ٹوٹ
    0.06
    لاک
    0.06
    sanity
    0.06
     أعلى
    0.06
     অসুর
    0.06
     एकदम
    0.06
     glacier
    0.06
    !");
    0.06
     ಜೋ
    0.06
    Activations Density 0.012%

    No Known Activations