© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4154
    Prev
    Next
    INDEX
    Explanations

    sports competitions and comparisons

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

    The neuron activates on named entities—proper names of people, teams, leagues, and similar capitalized titles.

    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
     ти
    -0.73
     உ
    -0.71
     меж
    -0.70
     чи
    -0.69
     watering
    -0.68
    campaign
    -0.67
     Ravi
    -0.66
     yang
    -0.66
     ý
    -0.65
     sleek
    -0.65
    POSITIVE LOGITS
     Lakers
    0.98
     Shaq
    0.98
    ването
    0.86
     Kame
    0.85
     Jerman
    0.84
     guerres
    0.84
     তার
    0.82
     LAP
    0.78
     armament
    0.78
     Toshiba
    0.78
    Activations Density 0.008%

    No Known Activations