© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106230
    Prev
    Next
    INDEX
    Explanations

    funeral cemetery burial coffin mourners

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

    The neuron fires on mentions of official mortuary‐affairs or burial‐service terms (e.g. “Mortuary Affairs” and related retrieval/transport/burial language).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     počíta
    -0.85
    ilions
    -0.78
     stunted
    -0.74
     devront
    -0.74
     Acne
    -0.73
     parable
    -0.72
    uyasha
    -0.72
    ranet
    -0.71
     exiled
    -0.71
    詔
    -0.71
    POSITIVE LOGITS
     funeral
    3.98
     Funeral
    3.34
     burial
    3.27
    funeral
    3.08
    Funeral
    3.06
     cemetery
    2.91
     funerals
    2.80
     funer
    2.73
     coffin
    2.72
     mourners
    2.63
    Activations Density 0.111%

    No Known Activations