© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21323
    Prev
    Next
    INDEX
    Explanations

    funeral and obituary announcements

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

    The neuron detects obituary and death-announcement language, such as “passed away,” “funeral,” and other markers of someone’s death.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    obituaries and death-related announcements, especially phrases indicating a person has died and information about funerals or memorial services.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    obituaries and death announcements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    擽
    -1.77
    镲
    -1.71
    神
    -1.62
     estrutura
    -1.60
     และ
    -1.59
    甚至
    -1.58
    𝅥
    -1.55
    ↵↵
    -1.55
    ՚
    -1.52
     パリ
    -1.48
    POSITIVE LOGITS
     with
    2.11
     as
    2.09
     still
    1.95
     has
    1.90
     one
    1.87
     at
    1.80
     while
    1.73
     now
    1.71
     after
    1.66
     in
    1.62
    Activations Density 0.001%

    No Known Activations