© 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. 105979
    Prev
    Next
    INDEX
    Explanations

    taxi rides and services

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

    The main thing this neuron does is find occurrences of the word “taxi” (including its inflected forms like “taxiing”).

    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
     –
    -3.39
    撄
    -3.03
    ،
    -3.00
    麁
    -2.95
    1
    -2.94
    '
    -2.91
    ।
    -2.78
    夲
    -2.77
    寕
    -2.64
     eleições
    -2.59
    POSITIVE LOGITS
    𓋼
    2.83
    e
    2.61
     ...
    2.50
    鉭
    2.47
     Both
    2.47
     
    2.28
    歩く
    2.27
     These
    2.27
    ዡ
    2.23
     lograr
    2.22
    Activations Density 0.004%

    No Known Activations