© 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. 21107
    Prev
    Next
    INDEX
    Explanations

    players after names

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

    This neuron activates on capitalized names of people—especially footballers, managers, and related proper names.

    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
     its
    -1.32
     it
    -1.30
     både
    -1.25
     each
    -1.24
     bơm
    -1.21
     depoz
    -1.21
    Also
    -1.20
    既存
    -1.19
     皿
    -1.18
     this
    -1.14
    POSITIVE LOGITS
    じゃなくて
    1.45
     quien
    1.43
             
    1.39
                   
    1.37
                         
    1.31
     who
    1.30
    については
    1.29
                  
    1.29
               
    1.28
          
    1.27
    Activations Density 0.026%

    No Known Activations