© 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. 116875
    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
    ndash
    -0.07
     Quando
    -0.06
     Cuando
    -0.06
     അതേ
    -0.06
     Rabu
    -0.06
     ایالات
    -0.06
    Quando
    -0.06
     Setelah
    -0.06
     Потому
    -0.06
     navegar
    -0.06
    POSITIVE LOGITS
     ইউনিভার
    0.07
     ছিলাম
    0.06
    少年
    0.06
     can
    0.06
    と
    0.05
     લાવ
    0.05
    руя
    0.05
    や
    0.05
     as
    0.05
     like
    0.05
    Activations Density 0.000%

    No Known Activations