© 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. 118256
    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
     გახ
    -0.06
     ежеднев
    -0.06
     accepter
    -0.06
     extracts
    -0.06
    corso
    -0.06
     Jackpot
    -0.06
    สะอาด
    -0.06
     ব্যক্তিকে
    -0.06
    achusetts
    -0.05
     Aleksandar
    -0.05
    POSITIVE LOGITS
     on
    0.06
    sibling
    0.06
     desde
    0.06
     since
    0.06
    🤱
    0.06
     পঞ্চম
    0.06
     Newborn
    0.05
    🌬
    0.05
    🎑
    0.05
     पराम
    0.05
    Activations Density 0.000%

    No Known Activations