© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45115
    Prev
    Next
    INDEX
    Explanations

    proper nouns and common starters

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

    The neuron activates on the double‐curly‐brace sequence "{{", i.e. the start of a template in wiki‐style markup.

    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
     if
    -2.02
     
    -1.95
    用于
    -1.73
     ancak
    -1.61
     should
    -1.57
    [
    -1.57
     in
    -1.52
     while
    -1.50
     keď
    -1.49
     did
    -1.48
    POSITIVE LOGITS
    WebElementEntity
    2.02
     rimasto
    1.91
    雰囲
    1.90
    媃
    1.84
     scattata
    1.78
     spécifique
    1.77
     男の子
    1.74
     arrivato
    1.73
     situato
    1.72
     venuto
    1.70
    Activations Density 0.000%

    No Known Activations