© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7777
    Prev
    Next
    INDEX
    Explanations

    funeral ceremony or talk

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

    This neuron detects mentions of funeral or memorial service announcements (e.g. “Memorial service will be held,” “graveside service,” etc.).

    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
    uot
    0.62
    붓
    0.56
    њу
    0.53
    Ἠ
    0.53
     tribut
    0.51
     morn
    0.51
    cję
    0.50
    ἂ
    0.50
     tribute
    0.50
     homage
    0.49
    POSITIVE LOGITS
     आवृ
    0.70
     Focusing
    0.70
     selanjutnya
    0.69
     Oyun
    0.68
     Archiv
    0.68
     USAID
    0.68
     Designing
    0.66
     Adapted
    0.65
     Webinar
    0.64
     Obsidian
    0.64
    Activations Density 0.002%

    No Known Activations