© 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. 118481
    Prev
    Next
    INDEX
    Explanations

    jumped

    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
    访问
    -0.06
    訪問
    -0.06
     embassy
    -0.06
     visite
    -0.06
     Combine
    -0.06
    场合
    -0.06
    Presentation
    -0.06
     strolling
    -0.06
     visita
    -0.06
     street
    -0.06
    POSITIVE LOGITS
     insists
    0.07
     relentless
    0.06
    よろしく
    0.06
     unrelenting
    0.06
     bardziej
    0.06
     maine
    0.06
     insisting
    0.06
    ✊
    0.06
    bullets
    0.06
     sniping
    0.06
    Activations Density 0.021%

    No Known Activations