© 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. 84948
    Prev
    Next
    INDEX
    Explanations

    Kanye West

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

    The neuron fires on capitalized named entities—particularly personal names and other proper‐noun tokens.

    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
     continuare
    -1.13
     objedná
    -1.08
    Amerika
    -1.05
     during
    -1.03
    ﺁ
    -1.02
     Selama
    -1.02
    Fuer
    -1.00
     prodej
    -0.99
     kunjungan
    -0.99
     Pilihan
    -0.99
    POSITIVE LOGITS
    /
    1.06
    那天
    0.96
      
    0.96
    .[
    0.93
     pervasive
    0.92
     misleading
    0.91
     fogo
    0.91
     +
    0.91
          
    0.90
            
    0.89
    Activations Density 0.000%

    No Known Activations