© 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. 34-GEMMASCOPE-RES-131K
    7. 119250
    Prev
    Next
    INDEX
    Explanations

    names starting with Don

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

    The neuron fires on occurrences of the proper name “Don” (including “Donald”) in 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_34/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
    ButtonGroup
    -0.85
     contention
    -0.84
     deb
    -0.76
    DEB
    -0.73
    dall
    -0.71
    uración
    -0.71
     gostar
    -0.71
    MenuBar
    -0.70
     QtGui
    -0.70
    Override
    -0.70
    POSITIVE LOGITS
    Aper
    0.78
    
    0.69
    ところ
    0.69
     normalmente
    0.68
     moderated
    0.68
     querida
    0.68
    かというと
    0.68
     Sart
    0.66
     threads
    0.66
    קס
    0.66
    Activations Density 0.046%

    No Known Activations