© 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. 118978
    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
    種類の
    -0.06
     for
    -0.06
     habitually
    -0.06
     것이
    -0.06
    і
    -0.06
     during
    -0.06
     spezielle
    -0.05
    ဢ
    -0.05
     숫
    -0.05
    <b>
    -0.05
    POSITIVE LOGITS
     a
    0.07
     lauded
    0.06
     the
    0.06
    邀請
    0.06
     circuit
    0.06
     Gary
    0.06
     Margaret
    0.06
    нів
    0.06
    гация
    0.06
    KOH
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.