© 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. 58930
    Prev
    Next
    INDEX
    Explanations

    sports teams and ranks

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

    The neuron identifies mentions of a club’s “first team” or “first-team squad,” i.e. references to the senior/main team.

    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
    geſ
    -2.47
      
    -2.42
             
    -2.02
        
    -1.95
           
    -1.83
     outros
    -1.82
                  
    -1.76
         
    -1.75
                                   
    -1.71
                              
    -1.70
    POSITIVE LOGITS
    c
    1.95
    卨
    1.85
    an
    1.84
    怎么回事
    1.80
    }
    1.79
    櫺
    1.77
    m
    1.77
    t
    1.77
    賒
    1.67
    ar
    1.63
    Activations Density 0.009%

    No Known Activations