© 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. 129126
    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
     pärast
    -0.06
     Stretch
    -0.06
     AFTER
    -0.06
     Known
    -0.06
    enough
    -0.06
     when
    -0.06
     M
    -0.06
     Kits
    -0.05
     at
    -0.05
     extensible
    -0.05
    POSITIVE LOGITS
    𝐛
    0.07
    正则表达式
    0.06
    ということで
    0.06
     still
    0.06
    カッコ
    0.06
    こう
    0.06
     importantly
    0.06
     অন্ধকার
    0.06
     three
    0.06
    こういう
    0.06
    Activations Density 0.000%

    No Known Activations