© 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. 130353
    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
     pernicious
    -0.06
    ule
    -0.06
    .............
    -0.05
     substantial
    -0.05
     ,"
    -0.05
     প্রচন্ড
    -0.05
     হাইকমি
    -0.05
     மிகப்
    -0.05
     widely
    -0.05
     analogous
    -0.05
    POSITIVE LOGITS
     finished
    0.06
     pentru
    0.06
     Finished
    0.06
     perquè
    0.06
    finished
    0.06
     علشان
    0.06
    Knife
    0.06
     Cosmic
    0.06
     for
    0.06
     පරි
    0.06
    Activations Density 0.000%

    No Known Activations