© 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. 119042
    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
    ماً
    -0.07
    飙
    -0.06
     zichzelf
    -0.06
    бычно
    -0.06
     আপনি
    -0.06
     kanske
    -0.06
    太太
    -0.06
     enero
    -0.06
    ugd
    -0.06
    人の
    -0.06
    POSITIVE LOGITS
     also
    0.09
     two
    0.07
    new
    0.07
    two
    0.07
     which
    0.07
    also
    0.06
     también
    0.06
    useful
    0.06
     নিয়েও
    0.06
     via
    0.06
    Activations Density 0.000%

    No Known Activations