© 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. 119416
    Prev
    Next
    INDEX
    Explanations

    names of people and organizations

    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
     all
    -0.09
     William
    -0.07
     Richard
    -0.07
    全て
    -0.06
     Marm
    -0.06
     Xerox
    -0.06
     Stephen
    -0.06
     George
    -0.06
    eb
    -0.06
    sembly
    -0.06
    POSITIVE LOGITS
     aumentado
    0.06
     збіль
    0.06
     leftist
    0.06
     haver
    0.06
     aumentando
    0.06
    至今
    0.06
    larger
    0.06
    している
    0.06
     jasno
    0.06
     getting
    0.06
    Activations Density 0.001%

    No Known Activations