© 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. 117328
    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
     الأرض
    -0.05
    तांत्रिक
    -0.05
     नव्हते
    -0.05
     preferable
    -0.05
    four
    -0.05
    '_
    -0.05
     horrific
    -0.05
     পারিনি
    -0.05
    five
    -0.05
    则
    -0.05
    POSITIVE LOGITS
    ú
    0.06
     diffusion
    0.06
     bahan
    0.06
    肌肉
    0.06
     CJ
    0.06
     Dairy
    0.06
    Diffusion
    0.06
    胿
    0.06
    ósito
    0.06
    所以
    0.06
    Activations Density 0.000%

    No Known Activations