© 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. 116885
    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
    Let
    -0.06
     Distinguished
    -0.06
    逹
    -0.06
    There
    -0.06
    It
    -0.06
     Denver
    -0.06
    ಕರ
    -0.05
    They
    -0.05
    知道
    -0.05
    检查
    -0.05
    POSITIVE LOGITS
     Dokument
    0.06
     Drawings
    0.06
     vriend
    0.06
     olarak
    0.06
     drugih
    0.06
     продаже
    0.06
    壃
    0.06
     Ac
    0.06
     betekent
    0.06
    TypeName
    0.06
    Activations Density 0.000%

    No Known Activations