© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102642
    Prev
    Next
    INDEX
    Explanations

    sports and organizations

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

    The neuron fires selectively on the names and labels of sports clubs, leagues, and youth‐sports programs.

    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
    </h2>
    -1.55
    $
    -1.38
    ↵↵↵↵
    -1.38
     mientras
    -1.30
    how
    -1.22
     garantiza
    -1.21
     terá
    -1.20
     tenemos
    -1.20
    ↵↵↵
    -1.18
     tampoco
    -1.18
    POSITIVE LOGITS
     them
    1.87
     for
    1.66
    жены
    1.29
     ними
    1.22
    των
    1.20
     jika
    1.19
    लिए
    1.18
    ënt
    1.13
    postIndex
    1.12
     ผ
    1.11
    Activations Density 0.045%

    No Known Activations