© 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. 129727
    Prev
    Next
    INDEX
    Explanations

    "explain" or "question"

    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
    地区
    -0.06
     शोषण
    -0.06
     implemented
    -0.06
    थित
    -0.06
    opherol
    -0.06
    haha
    -0.06
    地区的
    -0.06
    Apply
    -0.06
     ऑफर
    -0.06
    前者
    -0.06
    POSITIVE LOGITS
     Glossary
    0.06
    Explain
    0.06
     fundamentales
    0.06
    formats
    0.06
     answer
    0.06
     jednou
    0.06
     czym
    0.06
     explain
    0.06
     الفرق
    0.06
     Kash
    0.06
    Activations Density 0.112%

    No Known Activations