© 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. 117634
    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
     medio
    -0.06
    有些
    -0.06
    लीज
    -0.06
     enveloping
    -0.06
     ทำให้
    -0.06
     extent
    -0.06
     towards
    -0.06
     to
    -0.06
     allt
    -0.06
    用来
    -0.06
    POSITIVE LOGITS
     mientras
    0.06
     сообщил
    0.06
     или
    0.06
     крупней
    0.06
     informó
    0.06
    今年的
    0.06
     управ
    0.06
    するなど
    0.06
     దశ
    0.06
    লোক
    0.06
    Activations Density 0.000%

    No Known Activations