© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119021
    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
     chh
    -0.06
     globally
    -0.06
     .*
    -0.05
     કંપની
    -0.05
    lipped
    -0.05
     Pieces
    -0.05
     உலக
    -0.05
     global
    -0.05
     avanc
    -0.05
    import
    -0.05
    POSITIVE LOGITS
    典型的
    0.06
     myös
    0.06
     langage
    0.06
     elektrische
    0.06
    ULES
    0.06
     obtenido
    0.06
    每個
    0.06
     respectivos
    0.06
    uffix
    0.06
     penurunan
    0.06
    Activations Density 0.000%

    No Known Activations