© 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. 119920
    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
     ninety
    -0.06
     crucially
    -0.06
     quartier
    -0.06
     the
    -0.06
     zudem
    -0.06
     nine
    -0.06
     a
    -0.06
    Características
    -0.06
    rafts
    -0.06
     inoltre
    -0.06
    POSITIVE LOGITS
    ここでは
    0.06
    低
    0.06
     शोषण
    0.06
     وهنا
    0.06
     अगस्त
    0.06
     كل
    0.06
     다시
    0.06
     低
    0.06
     என்னும்
    0.06
     子
    0.05
    Activations Density 0.001%

    No Known Activations