© 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. 118981
    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
    记录
    -0.06
    నున్న
    -0.06
     this
    -0.05
     তালিকায়
    -0.05
     данном
    -0.05
    little
    -0.05
    enan
    -0.05
    尚
    -0.05
     बुरी
    -0.05
     চরিত্রে
    -0.05
    POSITIVE LOGITS
    情形
    0.06
    pearl
    0.06
     ακόμη
    0.06
    originalname
    0.06
     maple
    0.06
     Markdown
    0.06
    字母
    0.06
     résultats
    0.06
    ascimento
    0.06
     Spanish
    0.06
    Activations Density 0.000%

    No Known Activations