© 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. 119004
    Prev
    Next
    INDEX
    Explanations

    javascript code structure

    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
     최종
    -0.06
     ammunition
    -0.06
     करते
    -0.06
     концу
    -0.06
     cranberry
    -0.06
     definição
    -0.06
     vitally
    -0.06
     ឬ
    -0.06
     accusations
    -0.06
     both
    -0.05
    POSITIVE LOGITS
     haciendo
    0.07
    reading
    0.06
     Like
    0.05
    nius
    0.05
    Reading
    0.05
     рели
    0.05
     यज्ञ
    0.05
     ofreci
    0.05
     same
    0.05
     ஏற்றுக்கொள்ள
    0.05
    Activations Density 0.011%

    No Known Activations