© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130911
    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
     Elias
    -0.07
     احد
    -0.07
     aspectos
    -0.07
     podczas
    -0.07
     இறுதி
    -0.07
     Каждый
    -0.07
     Abdel
    -0.06
     необходимо
    -0.06
     potrebbe
    -0.06
     aspetti
    -0.06
    POSITIVE LOGITS
     came
    0.06
     for
    0.06
     gekommen
    0.05
    There
    0.05
     there
    0.05
     ही
    0.05
     llegaron
    0.05
     আরো
    0.05
     never
    0.05
    NOTE
    0.05
    Activations Density 0.000%

    No Known Activations