© 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. 22165
    Prev
    Next
    INDEX
    Explanations

    names of people and metformin

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

    The neuron detects personal given names (first names) in the text.

    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
    ↵
    -4.22
    ↵↵
    -3.45
    擽
    -2.84
    曁
    -2.78
    ꈊ
    -2.63
    
    -2.52
    鴣
    -2.52
    
    -2.48
    珖
    -2.44
     você
    -2.41
    POSITIVE LOGITS
     支援
    2.84
    できました
    2.72
     Armies
    2.59
    </tfoot>
    2.52
    孖
    2.47
     ساعة
    2.41
     歳
    2.36
     ersche
    2.33
     المياه
    2.31
    されていた
    2.27
    Activations Density 0.003%

    No Known Activations