© 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. 129524
    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
     so
    -0.06
    とした
    -0.06
     शेड्यूल
    -0.06
     보기
    -0.06
     মাঝ
    -0.06
    安排
    -0.05
     خدمت
    -0.05
     உட
    -0.05
    día
    -0.05
    <eos>
    -0.05
    POSITIVE LOGITS
     initial
    0.07
     również
    0.07
     myös
    0.07
     anche
    0.07
     επίσης
    0.07
     ALSO
    0.07
    大量
    0.07
     also
    0.07
    早在
    0.07
     primarily
    0.07
    Activations Density 0.000%

    No Known Activations