© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31968
    Prev
    Next
    INDEX
    Explanations

    Mexican revolution, Lucha Libre, Mexico City

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

    The neuron activates on occurrences of the word “Mexican,” flagging mentions of that nationality or related term.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Capitán
    -1.07
     Canarias
    -1.00
     león
    -0.99
     Energía
    -0.98
     Compañía
    -0.97
     Atlántico
    -0.96
     Comunidad
    -0.95
     Bahía
    -0.93
     Gonçalves
    -0.89
     cubano
    -0.88
    POSITIVE LOGITS
     Mexico
    3.05
    Mexico
    2.64
     Mexican
    2.63
    Mexican
    2.28
     mexico
    2.00
    MEX
    1.92
     Мекси
    1.80
    墨西哥
    1.79
     Mexicans
    1.76
    mexico
    1.70
    Activations Density 0.067%

    No Known Activations