© 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. 117897
    Prev
    Next
    INDEX
    Explanations

    sections and codes

    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
     администра
    -0.06
     connects
    -0.06
     when
    -0.06
    舝
    -0.06
    또한
    -0.06
     луч
    -0.06
     Booklet
    -0.06
     whenever
    -0.06
     специфи
    -0.06
    
    -0.06
    POSITIVE LOGITS
     new
    0.10
     yeni
    0.09
     nowych
    0.09
     neue
    0.09
     nuevos
    0.09
     nieuwe
    0.09
     nowe
    0.09
    ใหม่
    0.08
     новый
    0.08
     новых
    0.08
    Activations Density 0.002%

    No Known Activations