© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57857
    Prev
    Next
    INDEX
    Explanations

    opening and closing ceremonies olympics

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

    The neuron strongly activates on tokens naming major international multi‐sport events and their ceremonies (e.g. “Olympics,” “opening/closing ceremony,” “Asian Games,” etc.).

    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
     premio
    -0.68
     phosphatase
    -0.67
    ́n
    -0.67
    tiera
    -0.67
    bersicht
    -0.66
     arcade
    -0.66
     lingerie
    -0.65
     സ
    -0.65
    query
    -0.65
    guntas
    -0.64
    POSITIVE LOGITS
     Opening
    2.28
     torch
    2.17
     opening
    2.06
    Opening
    2.02
    torch
    1.73
     OPENING
    1.70
     Torch
    1.67
    opening
    1.65
    OPENING
    1.59
    Torch
    1.57
    Activations Density 0.018%

    No Known Activations