© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118307
    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
    やはり
    -0.07
    โย
    -0.06
     нескольких
    -0.06
    пи
    -0.06
     esclusivamente
    -0.06
     экстре
    -0.06
    Ки
    -0.06
    決
    -0.06
     मसलन
    -0.06
    ylan
    -0.05
    POSITIVE LOGITS
    不去
    0.07
     whose
    0.07
     if
    0.07
     उत्पन्न
    0.06
    不懂
    0.06
     deren
    0.06
     새로
    0.06
    illiams
    0.06
    产生的
    0.06
     through
    0.06
    Activations Density 0.000%

    No Known Activations