© 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. 34-GEMMASCOPE-RES-131K
    7. 94163
    Prev
    Next
    INDEX
    Explanations

    Jordan, Q, Focusing on

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

    The neuron strongly activates on mentions of the “Air Jordan” sneaker name (including its subword pieces like “Air,” “Jordan,” “Jord,” “ans,” model numbers, and colorway 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_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
     Whittier
    -0.82
    Якщо
    -0.80
     fuji
    -0.80
    𝟘
    -0.77
     strug
    -0.77
     RUNNING
    -0.76
     Executors
    -0.76
    צים
    -0.76
    镖
    -0.75
    Rad
    -0.75
    POSITIVE LOGITS
     AJ
    0.99
     High
    0.81
     Retro
    0.79
     Low
    0.77
     Flight
    0.75
     Bench
    0.71
     high
    0.71
    andet
    0.69
    しかも
    0.69
     low
    0.68
    Activations Density 0.007%

    No Known Activations