© 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. 119347
    Prev
    Next
    INDEX
    Explanations

    game genres and simulation games

    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
    aksha
    -0.06
     استفاده
    -0.06
     использовании
    -0.06
     swift
    -0.06
     рит
    -0.06
    akrishna
    -0.06
     나머지
    -0.06
     apresentar
    -0.06
     propriétaire
    -0.06
     skillful
    -0.06
    POSITIVE LOGITS
     Informationen
    0.06
     yn
    0.05
     interns
    0.05
     Fas
    0.05
     Nail
    0.05
     vents
    0.05
     analyst
    0.05
    %';
    0.05
     ಉಪ
    0.05
    ಂಕ
    0.05
    Activations Density 0.011%

    No Known Activations