© 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. 104440
    Prev
    Next
    INDEX
    Explanations

    coach or coaches

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

    The neuron detects mentions of bus or coach (passenger-transport) vehicles and services.

    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
    ↵↵
    -1.54
    especially
    -1.51
     jejich
    -1.50
     and
    -1.39
     helyzet
    -1.37
     localizar
    -1.35
     Vereinigung
    -1.34
     serán
    -1.32
     aún
    -1.28
     RAJ
    -1.28
    POSITIVE LOGITS
    𐄙
    1.57
    履歴
    1.41
     guerrero
    1.41
    問題は
    1.40
     piscina
    1.38
    s
    1.35
     defStyleAttr
    1.34
    身子
    1.34
    時刻
    1.30
    Brainz
    1.30
    Activations Density 0.021%

    No Known Activations