© 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. 90399
    Prev
    Next
    INDEX
    Explanations

    journal year followed by semicolon

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

    The neuron is strongly activated by numeric tokens (e.g. years, volume/page numbers) in reference citations.

    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
     bepa
    -1.78
    fotograf
    -1.77
     після
    -1.73
     setelah
    -1.71
     untill
    -1.66
     Publicar
    -1.66
    komfort
    -1.62
     ';
    -1.61
     ако
    -1.60
     给
    -1.59
    POSITIVE LOGITS
     
    1.93
      
    1.91
     by
    1.80
    M
    1.74
     M
    1.73
    R
    1.73
     c
    1.71
    T
    1.70
     V
    1.70
    "
    1.70
    Activations Density 0.005%

    No Known Activations