© 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. 10072
    Prev
    Next
    INDEX
    Explanations

    Mass or ceremony

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

    The main thing this neuron does is detect references to scheduled event times and dates for funeral or visitation services.

    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
    鞠
    0.57
     fondos
    0.54
    ดอก
    0.54
    ints
    0.53
     dancers
    0.53
     cemeteries
    0.53
     nights
    0.52
    占
    0.52
    cat
    0.49
     memorials
    0.49
    POSITIVE LOGITS
     célébr
    0.63
     enzym
    0.60
     commutative
    0.60
    🔁
    0.56
     Dl
    0.55
     celebrar
    0.55
     dl
    0.54
     unir
    0.54
     Ministerio
    0.54
     silvest
    0.54
    Activations Density 0.041%

    No Known Activations