© 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. 119227
    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
     лишь
    -0.07
     بنی
    -0.06
     sheer
    -0.06
     merely
    -0.06
     असफल
    -0.06
     겸
    -0.06
     سیستم
    -0.06
    是个
    -0.06
     কাঠ
    -0.06
     pitfalls
    -0.06
    POSITIVE LOGITS
    震撼
    0.06
     nettoyer
    0.06
     anarchist
    0.06
     damaged
    0.06
    omani
    0.06
    (/^
    0.05
     Madness
    0.05
    Bey
    0.05
     calent
    0.05
     aguas
    0.05
    Activations Density 0.000%

    No Known Activations