© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13097
    Prev
    Next
    INDEX
    Explanations

    generate code or configuration

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

    The neuron activates on instances of the word “generate.”

    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
    횃
    -2.86
    鰨
    -2.75
    鵙
    -2.69
    
    -2.66
    釹
    -2.63
    ી
    -2.61
    綣
    -2.61
    Setiap
    -2.61
    岖
    -2.53
    ಿ
    -2.48
    POSITIVE LOGITS
     –
    3.61
     and
    3.28
     —
    2.95
     ‘‘
    2.83
     ‘’
    2.80
    霂
    2.77
     ”
    2.67
    ):
    2.55
        
    2.52
    ’,
    2.42
    Activations Density 0.045%

    No Known Activations