© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130866
    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
    公元
    -0.07
    andosi
    -0.06
     erected
    -0.06
    能够在
    -0.06
    と言
    -0.06
    উন্ড
    -0.06
    +(
    -0.06
    способ
    -0.06
     കോടതി
    -0.05
    মেন্ট
    -0.05
    POSITIVE LOGITS
     gebru
    0.06
     at
    0.06
     दक्षि
    0.06
     prints
    0.06
     for
    0.06
     in
    0.06
     obtain
    0.06
     crim
    0.06
     jual
    0.06
     Interesse
    0.06
    Activations Density 0.000%

    No Known Activations