© 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. 87365
    Prev
    Next
    INDEX
    Explanations

    a word describing a noun

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

    The neuron is triggered by the standalone single-character token “a.”

    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
     in
    -1.97
     but
    -1.94
     two
    -1.78
     three
    -1.77
     on
    -1.68
     four
    -1.54
     at
    -1.52
     five
    -1.50
     and
    -1.47
     by
    -1.43
    POSITIVE LOGITS
    ︲
    1.77
     جدید
    1.59
    ᠋
    1.57
    
    1.52
    真的很
    1.49
    的呢
    1.45
    such
    1.41
     SUCH
    1.40
     nouvelles
    1.38
     inconsciente
    1.38
    Activations Density 0.133%

    No Known Activations