© 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. 119739
    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
     writings
    -0.06
    terna
    -0.06
    ขณะ
    -0.06
     ईस्ट
    -0.06
     fiasco
    -0.06
     acclaimed
    -0.05
    ھے
    -0.05
     after
    -0.05
    тность
    -0.05
     পারছে
    -0.05
    POSITIVE LOGITS
     další
    0.07
     sugar
    0.07
    Sugar
    0.06
    检验
    0.06
     Argu
    0.06
     otros
    0.06
     sonst
    0.06
    expensive
    0.06
     মূলত
    0.06
    additional
    0.06
    Activations Density 0.000%

    No Known Activations