© 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. 117980
    Prev
    Next
    INDEX
    Explanations

    risk factors

    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
    Gior
    -0.06
     государ
    -0.06
     obsz
    -0.06
    他对
    -0.06
     qui
    -0.06
    竈
    -0.05
     requested
    -0.05
     argumento
    -0.05
    lul
    -0.05
     dele
    -0.05
    POSITIVE LOGITS
     aparición
    0.07
     preparación
    0.06
     सांगित
    0.06
     overlap
    0.06
    Overlap
    0.06
     venerable
    0.06
     TWO
    0.06
     によ
    0.06
    Approximately
    0.06
     common
    0.06
    Activations Density 0.013%

    No Known Activations