© 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. 130424
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     более
    -0.07
     ત્યાર
    -0.06
     více
    -0.06
     possède
    -0.06
     تاک
    -0.06
    公开
    -0.06
     již
    -0.06
     throughout
    -0.06
     seluruh
    -0.06
    более
    -0.06
    POSITIVE LOGITS
    约束
    0.07
     বিবেচনায়
    0.06
     ограничения
    0.06
    Because
    0.06
     Eldorado
    0.06
    eson
    0.06
    Using
    0.06
     Meadows
    0.06
    rud
    0.06
    enseignement
    0.06
    Activations Density 0.000%

    No Known Activations