© 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. 129147
    Prev
    Next
    INDEX
    Explanations

    license and neural net context

    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
     ग्रस्त
    -0.07
     έκ
    -0.06
    шений
    -0.06
     роско
    -0.06
     cataract
    -0.06
     组件
    -0.06
    funk
    -0.06
     Pandit
    -0.06
    вані
    -0.06
     funk
    -0.06
    POSITIVE LOGITS
     процеду
    0.06
    accurate
    0.06
     accurate
    0.06
     parting
    0.06
    accuracy
    0.06
     tools
    0.06
    Scotland
    0.06
    龙
    0.06
     "
    0.06
     time
    0.06
    Activations Density 0.011%

    No Known Activations