© 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. 130384
    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
     and
    -0.07
     if
    -0.06
     disponível
    -0.06
     And
    -0.06
     available
    -0.06
     disponible
    -0.06
     একই
    -0.06
     പക്ഷേ
    -0.06
     tersedia
    -0.06
     उपलब्ध
    -0.05
    POSITIVE LOGITS
    隹
    0.06
     Pakistani
    0.06
     Japon
    0.06
     உம்
    0.06
    শস্ত্র
    0.06
     __________
    0.06
     _____________
    0.06
     দিয়ে
    0.06
     गेहूं
    0.06
    的长
    0.06
    Activations Density 0.000%

    No Known Activations