© 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. 130917
    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
     asc
    -0.06
    ಡಿದ
    -0.06
    progressBar
    -0.06
     tang
    -0.05
     sinned
    -0.05
     decid
    -0.05
    turns
    -0.05
     longitudinally
    -0.05
     ξε
    -0.05
     و
    -0.05
    POSITIVE LOGITS
     Unless
    0.08
     unless
    0.07
    Unless
    0.07
    unless
    0.06
    ഡോ
    0.06
     whichever
    0.06
     باکس
    0.06
    astos
    0.06
     fixtures
    0.06
     اختبار
    0.06
    Activations Density 0.000%

    No Known Activations