© 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. 129166
    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
     tienen
    -0.06
     tiene
    -0.06
     primeiros
    -0.06
     menawarkan
    -0.06
    esseur
    -0.06
     toeg
    -0.06
    ર્ટ
    -0.05
     neither
    -0.05
     आरोग्य
    -0.05
    mentioned
    -0.05
    POSITIVE LOGITS
     riêng
    0.07
     gant
    0.06
    ूबी
    0.06
     leichter
    0.06
     간
    0.06
     дело
    0.06
     справа
    0.06
    jala
    0.06
     أي
    0.06
    余
    0.06
    Activations Density 0.000%

    No Known Activations