© 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. 130638
    Prev
    Next
    INDEX
    Explanations

    ventricular conditions

    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
     жінок
    -0.07
     kadın
    -0.07
     benar
    -0.06
     XII
    -0.06
     ladies
    -0.06
     kub
    -0.06
     governs
    -0.06
     kannst
    -0.06
     அப்படியே
    -0.06
     вернуть
    -0.06
    POSITIVE LOGITS
    European
    0.06
    歐洲
    0.06
     നിരവധി
    0.06
     countless
    0.06
    欧洲
    0.06
     only
    0.05
    national
    0.05
    无数
    0.05
     ಅನೇಕ
    0.05
    youth
    0.05
    Activations Density 0.009%

    No Known Activations