© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41946
    Prev
    Next
    INDEX
    Explanations

    free agent

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

    The neuron responds to mentions of free‐agency terms—especially the phrase “free agent” (and related tokens like “free,” “agent,” “agency,” “restricted”)—in player transaction contexts.

    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
    </h3>
    -1.77
        
    -1.77
    </em>
    -1.63
    苙
    -1.54
     процесс
    -1.50
     gewä
    -1.49
    
    -1.49
     ۶
    -1.48
     indican
    -1.44
     especialmente
    -1.42
    POSITIVE LOGITS
     for
    1.64
    i
    1.63
    
    1.55
    Татьяна
    1.54
    تنا
    1.52
     attaques
    1.45
     blessés
    1.45
     BorderRadius
    1.45
    }
    1.41
     murah
    1.40
    Activations Density 0.002%

    No Known Activations