© 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. 34612
    Prev
    Next
    INDEX
    Explanations

    cremation and amputation

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

    The neuron is keyed to the word “cremated.”

    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
     botan
    -0.90
    ternut
    -0.90
     aproximativ
    -0.88
     फल
    -0.81
     المؤس
    -0.81
     Botan
    -0.79
     dren
    -0.78
     jurídica
    -0.77
    níka
    -0.75
    <table>
    -0.74
    POSITIVE LOGITS
     cremation
    1.49
     Cremation
    1.24
     disposition
    1.03
    Cre
    1.02
     cre
    1.01
     Cre
    0.95
     İstanbul
    0.90
     incin
    0.88
    Disposition
    0.87
     şehir
    0.87
    Activations Density 0.009%

    No Known Activations