© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81144
    Prev
    Next
    INDEX
    Explanations

    funeral services

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

    The neuron is keyed to tokens that form part of multiword proper-names—place names, organizations, and other named entities.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     electrónico
    -0.80
     utilizados
    -0.78
    比べ
    -0.77
     puedas
    -0.77
     desarrollo
    -0.77
     cientí
    -0.75
     Forming
    -0.74
    的状态
    -0.74
     debería
    -0.74
    狀態
    -0.74
    POSITIVE LOGITS
     funeral
    2.25
     Funeral
    2.03
    Funeral
    1.58
    funeral
    1.48
     funerals
    1.45
     Mortuary
    1.20
     funer
    1.19
     FUNERAL
    1.17
     mort
    1.16
     Cremation
    1.11
    Activations Density 0.004%

    No Known Activations