© 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. 118657
    Prev
    Next
    INDEX
    Explanations

    fatal errors and exits

    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
     skirm
    -0.07
     cualquier
    -0.07
     time
    -0.06
     особое
    -0.06
     any
    -0.06
     янва
    -0.06
    ക്കി
    -0.06
    滌
    -0.06
     olds
    -0.06
     исти
    -0.06
    POSITIVE LOGITS
    commit
    0.07
    Percentage
    0.06
     উন্নয়নের
    0.06
     incorporate
    0.06
     hacker
    0.06
     incorpor
    0.05
     عد
    0.05
     incorporates
    0.05
     connector
    0.05
     üzerinde
    0.05
    Activations Density 0.002%

    No Known Activations