© 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. 118199
    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
     снова
    -0.07
     zowel
    -0.06
     både
    -0.06
     erneut
    -0.06
    দীর্ঘ
    -0.06
     কৃষি
    -0.06
     hogy
    -0.06
     zarówno
    -0.06
     काट
    -0.06
     மீண்டும்
    -0.06
    POSITIVE LOGITS
    several
    0.06
     ogni
    0.06
     каждым
    0.06
    این
    0.06
     $*$-
    0.06
     این
    0.05
    ешься
    0.05
     দলটি
    0.05
     десятки
    0.05
    ree
    0.05
    Activations Density 0.000%

    No Known Activations