© 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. 116322
    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
     मरीजों
    -0.06
     създа
    -0.06
     张
    -0.06
     finales
    -0.06
    ोने
    -0.06
     ネ
    -0.06
     yeni
    -0.06
    pitched
    -0.06
     For
    -0.06
    이지만
    -0.06
    POSITIVE LOGITS
    willing
    0.06
     oleh
    0.06
     compartido
    0.06
    মূল
    0.05
     tärke
    0.05
     varios
    0.05
    several
    0.05
     by
    0.05
     impracticable
    0.05
    誰も
    0.05
    Activations Density 0.000%

    No Known Activations