© 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. 130000
    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
     નહીં
    -0.07
    old
    -0.07
     sparked
    -0.06
     쉽
    -0.06
     Porque
    -0.06
     interpret
    -0.06
     perhaps
    -0.06
    艰
    -0.06
    Porque
    -0.06
     present
    -0.06
    POSITIVE LOGITS
     journalists
    0.06
     réparation
    0.06
    était
    0.06
    ictionnaire
    0.06
    Those
    0.06
    Emoji
    0.06
     Cajun
    0.06
     disclosure
    0.06
     gays
    0.06
     disclosures
    0.06
    Activations Density 0.000%

    No Known Activations