© 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. 128852
    Prev
    Next
    INDEX
    Explanations

    court cases

    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
    。
    -0.07
    事实上
    -0.07
    为
    -0.06
    .
    -0.06
    自带
    -0.05
    同时也
    -0.05
    wrapper
    -0.05
     கொண்டிருந்த
    -0.05
    anic
    -0.05
    Translated
    -0.05
    POSITIVE LOGITS
     sleeping
    0.06
     enthusi
    0.06
     cloths
    0.06
    咱们
    0.06
     spread
    0.06
     torpedo
    0.06
     नौकरी
    0.06
     दुसरे
    0.06
    ණය
    0.06
    医療
    0.06
    Activations Density 0.003%

    No Known Activations