© 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. 129122
    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
     they
    -0.06
     aforesaid
    -0.06
     representantes
    -0.06
     noteworthy
    -0.06
     הם
    -0.06
     unmistakable
    -0.06
     unmist
    -0.06
     transferring
    -0.05
     commented
    -0.05
     nichts
    -0.05
    POSITIVE LOGITS
    образие
    0.06
     една
    0.06
     generally
    0.06
     browns
    0.06
     lupus
    0.06
     generell
    0.06
    enseit
    0.06
     tolerance
    0.06
     grueso
    0.06
    귤
    0.06
    Activations Density 0.000%

    No Known Activations