© 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. 117614
    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
    我们可以
    -0.06
     niiden
    -0.06
     Bremen
    -0.06
     használ
    -0.06
     potentially
    -0.06
     우리가
    -0.06
     It
    -0.06
     Four
    -0.05
    ণি
    -0.05
     जनता
    -0.05
    POSITIVE LOGITS
     他
    0.06
    或其他
    0.06
    Already
    0.06
    Mask
    0.06
    🖌
    0.06
     সংখ্যা
    0.06
     և
    0.06
     dhe
    0.06
    🔒
    0.06
    이나
    0.06
    Activations Density 0.000%

    No Known Activations