© 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. 38976
    Prev
    Next
    INDEX
    Explanations

    Juventus and Yankees

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

    The neuron selectively activates on single-token, capitalized proper names—especially well-known brands or organizations (e.g. “Juventus,” “Yankees,” “GTR,” “Sinatra”).

    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
    ’,
    -2.39
     This
    -2.38
    .’’
    -2.23
    \
    -2.19
     Naturally
    -2.16
    鬭
    -2.08
    ."
    -2.08
    ਃ
    -2.05
     ‘
    -2.02
     年代
    -1.98
    POSITIVE LOGITS
    砦
    2.38
     帅气
    2.20
    
    2.19
    玊
    2.17
    辈子
    2.09
    であり
    2.08
     asfalto
    2.08
    鹩
    2.05
     และ
    2.05
     και
    2.05
    Activations Density 0.003%

    No Known Activations