© 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. 39186
    Prev
    Next
    INDEX
    Explanations

    articles followed by descriptive words

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

    The neuron fires on the “a” in the common pattern “That’s a …,” i.e. the article introducing an evaluative phrase like “That’s a beautiful …,” “That’s a good …,” 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
     lancia
    -1.86
     distru
    -1.66
     Instead
    -1.66
     Finally
    -1.64
     giochi
    -1.59
     vocale
    -1.59
     sento
    -1.57
     acque
    -1.53
     但
    -1.53
     But
    -1.53
    POSITIVE LOGITS
    全世界
    1.48
     tantas
    1.45
    ！(
    1.41
     a
    1.41
     an
    1.41
    
    1.41
     contund
    1.41
     universidades
    1.39
     salpic
    1.36
     reuniones
    1.34
    Activations Density 0.007%

    No Known Activations