© 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. 118494
    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
    也能
    -0.07
    がなく
    -0.06
     하지
    -0.06
    ukawa
    -0.06
    找不到
    -0.06
     maintain
    -0.06
    ບໍ່
    -0.06
     schauen
    -0.06
     looked
    -0.06
     বলতে
    -0.06
    POSITIVE LOGITS
     في
    0.07
     trong
    0.06
     donc
    0.06
    ঞ্ছ
    0.06
     apresentam
    0.06
    렀
    0.06
     Processor
    0.06
     nagy
    0.06
    קו
    0.06
     cuya
    0.06
    Activations Density 0.000%

    No Known Activations