© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14126
    Prev
    Next
    INDEX
    Explanations

    gold/silver medals

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

    The neuron flags numeric mentions of medals—especially counts of “gold” (and other) medals—in athlete biographies.

    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
     všech
    -1.67
    </h3>
    -1.59
    
    -1.55
     Futsal
    -1.55
     Pinn
    -1.52
    岀
    -1.48
     kteří
    -1.48
    BeginInit
    -1.45
    了过去
    -1.44
    
    -1.42
    POSITIVE LOGITS
     of
    2.34
     on
    2.06
     at
    1.69
    Unlike
    1.58
    While
    1.53
    From
    1.52
    こともある
    1.49
    珖
    1.44
    Without
    1.43
    Several
    1.42
    Activations Density 0.016%

    No Known Activations