© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110811
    Prev
    Next
    INDEX
    Explanations

    the word meeting

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

    The neuron reliably activates on the word “meeting.”

    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
     raven
    -2.91
    is
    -2.86
     kurzem
    -2.84
     $
    -2.78
     erase
    -2.66
    他在
    -2.59
    arraycopy
    -2.58
    ным
    -2.58
    的在
    -2.52
    TemporalType
    -2.50
    POSITIVE LOGITS
     stata
    3.27
    鈇
    3.25
    
    3.20
    砹
    3.05
    涷
    3.00
    鄠
    2.95
     Beſ
    2.91
    ⽼
    2.89
    酛
    2.86
    鋮
    2.66
    Activations Density 0.014%

    No Known Activations