© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71589
    Prev
    Next
    INDEX
    Explanations

    death care or official funerals

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

    The neuron strongly responds to words and phrases relating to death and burial—especially mentions of cemeteries, graves, dying, and caring for the dead.

    oai_token-act-pair · o4-miniTriggered 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
     reuters
    -1.24
     Sheng
    -1.24
     imediatamente
    -1.23
     nelson
    -1.21
     &
    -1.21
     laurent
    -1.20
     naquele
    -1.18
     patrick
    -1.16
     TORONTO
    -1.15
     MICHAEL
    -1.13
    POSITIVE LOGITS
     Lainnya
    1.42
     вместо
    1.33
     by
    1.26
     Menggunakan
    1.14
     vivere
    1.13
    ábado
    1.13
    8
    1.11
     Terkait
    1.10
     Memper
    1.10
     Pemain
    1.09
    Activations Density 0.104%

    No Known Activations