© 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. 22-GEMMASCOPE-RES-131K
    4. 39508
    Prev
    Next
    INDEX
    Explanations

    sports teams and places

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

    The neuron primarily detects mentions of sports leagues, teams, or other sporting organizations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     péché
    -1.00
     שר
    -0.98
    hists
    -0.96
    rrrrr
    -0.96
    かどうか
    -0.93
     grammes
    -0.92
    rrr
    -0.91
     chanteur
    -0.91
     nji
    -0.91
     volgens
    -0.91
    POSITIVE LOGITS
     why
    1.19
     Why
    1.19
     itself
    1.03
     refleja
    1.02
     basic
    0.99
     jeżeli
    0.98
     what
    0.98
    Очень
    0.97
     najdete
    0.96
     jednoduch
    0.95
    Activations Density 0.019%

    No Known Activations