© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11237
    Prev
    Next
    INDEX
    Explanations

    memorial service, funeral, or cremation details

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

    The neuron strongly activates on passages describing obituaries or funeral service details.

    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_31_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
     Apare
    0.63
     Survivors
    0.62
    Я
    0.61
     bereaved
    0.61
     मृतक
    0.59
    alena
    0.56
     Probate
    0.54
     Я
    0.52
    нови
    0.52
    🧅
    0.52
    POSITIVE LOGITS
     discretionary
    0.70
     privadas
    0.69
     privados
    0.66
     reception
    0.66
     consultancy
    0.64
     donations
    0.61
     private
    0.61
    攺
    0.61
     layanan
    0.60
     biking
    0.59
    Activations Density 0.023%

    No Known Activations