© 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. 120528
    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
    一种
    -0.07
    一個
    -0.07
     a
    -0.06
     một
    -0.06
    一種
    -0.06
    一个
    -0.06
    好多
    -0.06
    がたくさん
    -0.06
    初めて
    -0.06
     într
    -0.06
    POSITIVE LOGITS
    မှု
    0.06
     has
    0.06
     will
    0.06
     overwhelmingly
    0.06
     असली
    0.06
     realmente
    0.06
     reliably
    0.06
     वाकई
    0.06
     بھی
    0.06
     aside
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.