© 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. 117496
    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
     boyunca
    -0.08
     immensely
    -0.07
     Something
    -0.06
     ghostly
    -0.06
     അനുഭവ
    -0.06
     benefited
    -0.06
     سخت
    -0.06
    łącznie
    -0.06
     এখন
    -0.06
    तीन
    -0.06
    POSITIVE LOGITS
    Even
    0.06
     even
    0.06
     erster
    0.06
    even
    0.06
     ЗА
    0.06
    θέ
    0.06
    (!)
    0.06
     навіть
    0.06
     iguales
    0.06
     lâng
    0.06
    Activations Density 0.000%

    No Known Activations