© 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. 117631
    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
     módulo
    -0.07
    性别
    -0.07
     périphérique
    -0.07
     первую
    -0.07
     пър
    -0.06
    install
    -0.06
    东南
    -0.06
     läbi
    -0.06
     karşılaş
    -0.06
     ersten
    -0.06
    POSITIVE LOGITS
     Governmental
    0.06
    iguez
    0.05
     നല്ല
    0.05
     முன்ன
    0.05
    area
    0.05
    JF
    0.05
    ization
    0.05
     Based
    0.05
     worldwide
    0.05
    HD
    0.05
    Activations Density 0.000%

    No Known Activations