© 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. 130199
    Prev
    Next
    INDEX
    Explanations

    code example questions

    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
     worldview
    -0.06
     rarely
    -0.06
     infrequently
    -0.06
     Rarely
    -0.06
    可能会
    -0.06
    对面
    -0.05
     любого
    -0.05
    Насе
    -0.05
     view
    -0.05
     сторона
    -0.05
    POSITIVE LOGITS
     crean
    0.06
     kako
    0.06
     aici
    0.06
    CCCC
    0.06
    
    0.06
     اینجا
    0.05
     so
    0.05
     వు
    0.05
     chuyên
    0.05
     commencent
    0.05
    Activations Density 0.001%

    No Known Activations