© 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. 120126
    Prev
    Next
    INDEX
    Explanations

    debugging code

    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
     perforation
    -0.06
     combustion
    -0.06
    测试
    -0.06
    測試
    -0.06
     Inspect
    -0.06
     introspection
    -0.06
     testing
    -0.06
     affinities
    -0.06
     unaware
    -0.05
     intoler
    -0.05
    POSITIVE LOGITS
     มี
    0.07
     vad
    0.06
     পল্ল
    0.06
     നേടിയ
    0.06
     Three
    0.06
     Umgang
    0.06
     achieving
    0.06
     managing
    0.06
    **,
    0.06
     American
    0.06
    Activations Density 0.011%

    No Known Activations