© 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. 118542
    Prev
    Next
    INDEX
    Explanations

    secret agent spies undercover operative

    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
     solution
    -0.06
     KZ
    -0.06
    Solution
    -0.06
    슥
    -0.06
    মুর
    -0.05
    ).
    -0.05
     penis
    -0.05
     дори
    -0.05
     growing
    -0.05
     Solution
    -0.05
    POSITIVE LOGITS
    働
    0.07
     fourteen
    0.07
     seventeen
    0.07
     چندین
    0.07
     представители
    0.07
    试图
    0.06
     estudar
    0.06
     arbet
    0.06
     textbook
    0.06
     bekerja
    0.06
    Activations Density 0.013%

    No Known Activations