© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9246
    Prev
    Next
    INDEX
    Explanations

    death and illness information

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects obituary‐style death announcements—words and dates signaling that someone “died,” “passed away,” or similar.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     மற்றும்
    0.75
     openings
    0.64
     frequented
    0.63
     throughout
    0.63
     started
    0.62
     galore
    0.62
     Class
    0.62
     或
    0.62
     spawn
    0.61
     used
    0.61
    POSITIVE LOGITS
    疾病
    0.86
     śmier
    0.77
     menjalani
    0.76
     болезнь
    0.75
     علت
    0.73
    病的
    0.71
    痙
    0.71
     âgé
    0.70
     malattia
    0.70
     bahagia
    0.70
    Activations Density 0.027%

    No Known Activations