© 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. 129921
    Prev
    Next
    INDEX
    Explanations

    questions/case names followed by data identifiers

    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
    ujete
    -0.07
     making
    -0.07
     Making
    -0.06
     khiến
    -0.06
    合格
    -0.06
     these
    -0.06
    甚至
    -0.06
     ทำให้
    -0.06
    也有
    -0.06
     tienes
    -0.06
    POSITIVE LOGITS
     আশা
    0.06
    과는
    0.06
     dessen
    0.06
     ক্রস
    0.06
     twin
    0.06
     provavelmente
    0.06
    și
    0.06
     baseado
    0.06
     সুপার
    0.05
    इद
    0.05
    Activations Density 0.003%

    No Known Activations