© 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. 130897
    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
     primero
    -0.06
    義
    -0.06
     først
    -0.06
     first
    -0.06
     boundary
    -0.06
    mediation
    -0.06
    侄
    -0.06
     compromising
    -0.06
     krypt
    -0.06
     Indicator
    -0.05
    POSITIVE LOGITS
    ept
    0.06
     tissu
    0.06
     توضیح
    0.06
     таких
    0.06
     tax
    0.06
     పూర్తి
    0.06
     такого
    0.05
    того
    0.05
     taxa
    0.05
     Tender
    0.05
    Activations Density 0.000%

    No Known Activations