© 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. 67101
    Prev
    Next
    INDEX
    Explanations

    Watson

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

    The main thing this neuron does is detect the surname “Watson.”

    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
    
    -3.23
    歃
    -3.22
    
    -3.20
    ?"
    -3.14
    炝
    -3.14
    遄
    -3.11
    鳢
    -3.09
    ！！！
    -3.08
     menyen
    -3.05
    芣
    -3.03
    POSITIVE LOGITS
    -
    3.36
    ?
    3.14
    {
    2.97
     
    2.92
       
    2.75
    ↵
    2.72
    更为
    2.64
            
    2.63
     finds
    2.55
           
    2.53
    Activations Density 0.006%

    No Known Activations