© 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. 130213
    Prev
    Next
    INDEX
    Explanations

    names and familial roles

    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
     adopting
    -0.06
    与其他
    -0.06
    रोध
    -0.06
     subjected
    -0.06
     выполнения
    -0.06
     Cortes
    -0.06
     suffer
    -0.06
    自
    -0.06
     نتائج
    -0.06
    ริกา
    -0.06
    POSITIVE LOGITS
    单独
    0.06
     DEFIN
    0.06
     vér
    0.06
    我們
    0.06
    없
    0.06
    θεί
    0.06
     ください
    0.06
     কখনোই
    0.06
    ubwa
    0.06
    file
    0.05
    Activations Density 0.012%

    No Known Activations