© 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. 120172
    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
    그래서
    -0.07
     myös
    -0.07
    쫄
    -0.07
     Для
    -0.07
    色は
    -0.07
     остальные
    -0.07
     også
    -0.06
     üzerinde
    -0.06
    த்துள்ளனர்
    -0.06
    നു
    -0.06
    POSITIVE LOGITS
    ipsis
    0.06
    सर्जन
    0.06
     চীনা
    0.06
    !
    0.05
    Thomas
    0.05
     begins
    0.05
     one
    0.05
    <strong>
    0.05
     quietly
    0.05
    one
    0.05
    Activations Density 0.000%

    No Known Activations