© 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. 128862
    Prev
    Next
    INDEX
    Explanations

    herbs, spices, and ingredients

    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
    btn
    -0.06
     armado
    -0.06
    rain
    -0.06
     secretly
    -0.06
     تعلیم
    -0.06
     laporan
    -0.06
     tasarım
    -0.06
    process
    -0.06
     school
    -0.05
     resilient
    -0.05
    POSITIVE LOGITS
     uso
    0.07
     marketplace
    0.07
     brukes
    0.06
     usos
    0.06
     применять
    0.06
    현재
    0.06
     More
    0.06
    Markets
    0.06
     প্রতিনি
    0.06
    ร้าน
    0.06
    Activations Density 0.007%

    No Known Activations