© 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. 119143
    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
     comparing
    -0.06
     purple
    -0.06
     மஞ்சள்
    -0.06
    就会
    -0.05
    ichever
    -0.05
     কূটনৈতিক
    -0.05
     panic
    -0.05
     International
    -0.05
    спек
    -0.05
     해당
    -0.05
    POSITIVE LOGITS
     what
    0.06
    是如何
    0.06
     कराया
    0.06
     empir
    0.06
     permitted
    0.06
     COMMUNITY
    0.06
    ᱵ
    0.06
     approximation
    0.06
    enough
    0.06
     libre
    0.06
    Activations Density 0.000%

    No Known Activations