© 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. 117381
    Prev
    Next
    INDEX
    Explanations

    named, leads, posted, with, the

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     meglio
    -0.06
     جسم
    -0.06
    ஷ்ட
    -0.06
    身体
    -0.06
     while
    -0.06
    ки
    -0.05
    ке
    -0.05
     సంబంధ
    -0.05
     Educación
    -0.05
     अधिक
    -0.05
    POSITIVE LOGITS
     resampling
    0.06
     particulars
    0.06
     различными
    0.06
     различных
    0.06
     můžete
    0.06
     nejen
    0.06
     fisheries
    0.06
     различ
    0.06
    illance
    0.05
    ющимся
    0.05
    Activations Density 0.001%

    No Known Activations