© 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. 119371
    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
     環
    -0.06
     videre
    -0.06
    crystal
    -0.06
     excelled
    -0.06
     osserv
    -0.06
    áním
    -0.06
     intently
    -0.06
    ONE
    -0.06
    Around
    -0.06
    Thirty
    -0.05
    POSITIVE LOGITS
     some
    0.06
     транспорта
    0.06
     alguns
    0.06
     आय
    0.06
     रिएक्शन
    0.06
     tolerancia
    0.05
     फल
    0.05
    फल
    0.05
    设备的
    0.05
     baño
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.