© 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. 129323
    Prev
    Next
    INDEX
    Explanations

    legal titles and proceedings

    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
     tragically
    -0.08
     στιγμή
    -0.07
    Hiện
    -0.07
     Coroner
    -0.06
     actuellement
    -0.06
     traceability
    -0.06
     বিদ্যুৎ
    -0.06
     historical
    -0.06
    ంచి
    -0.06
    焚
    -0.06
    POSITIVE LOGITS
    女性
    0.07
     nowego
    0.06
    轻松
    0.06
     উপযোগী
    0.06
     нового
    0.06
    呸
    0.06
    輕鬆
    0.06
     Series
    0.06
     оди
    0.06
     Baud
    0.06
    Activations Density 0.028%

    No Known Activations