© 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. 118225
    Prev
    Next
    INDEX
    Explanations

    died or death event

    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
     Wallpaper
    -0.06
     ugl
    -0.06
    觉得
    -0.06
     inkl
    -0.06
     Rural
    -0.06
     وزارة
    -0.06
     clerks
    -0.06
     so
    -0.06
    lete
    -0.06
     veut
    -0.05
    POSITIVE LOGITS
     উইল
    0.06
     innovation
    0.06
    ﾛ
    0.06
     testator
    0.06
     proper
    0.06
    (#
    0.06
     necessary
    0.06
     કોઈપણ
    0.06
     সর্বো
    0.06
     সঠিকভাবে
    0.06
    Activations Density 0.005%

    No Known Activations