© 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. 118310
    Prev
    Next
    INDEX
    Explanations

    Bluetooth devices

    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
     provocative
    -0.06
    奮
    -0.06
     rifles
    -0.06
     inspir
    -0.06
     போரா
    -0.06
     الوطن
    -0.05
    ıcı
    -0.05
     inspiration
    -0.05
     dynam
    -0.05
    Utah
    -0.05
    POSITIVE LOGITS
    相關
    0.07
    相关的
    0.07
    कुमारी
    0.06
     denture
    0.06
     relacionado
    0.06
     especializado
    0.06
     piccola
    0.06
    🆗
    0.06
     vinculado
    0.06
     relacionados
    0.06
    Activations Density 0.007%

    No Known Activations