© 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. 10-GEMMASCOPE-RES-131K
    7. 120097
    Prev
    Next
    INDEX
    Explanations

    e-commerce

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

    The neuron is keyed to spotting the standalone “e” prefix in hyphenated terms (e-mail, e-commerce, e-books, etc.).

    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
    ↵
    -2.73
     who
    -1.97
     
    -1.94
     Moreover
    -1.68
     ebenfalls
    -1.66
    <td>
    -1.64
     vollen
    -1.59
    非常
    -1.55
     也
    -1.48
    很少
    -1.45
    POSITIVE LOGITS
    蟊
    2.17
    borderSide
    2.06
     現貨
    1.89
    嗵
    1.84
    喁
    1.84
     cél
    1.83
    OURCES
    1.80
    ！"
    1.79
     fundamentos
    1.78
    ADORES
    1.77
    Activations Density 0.024%

    No Known Activations