© 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. 11956
    Prev
    Next
    INDEX
    Explanations

    sports scores and teams

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

    This neuron fires on instances of the phrase “watching the,” i.e. mentions of watching something.

    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
    Distribución
    -0.75
    Instrucciones
    -0.72
    厉
    -0.68
    青森
    -0.68
    vest
    -0.68
    Fp
    -0.66
    decla
    -0.66
     duro
    -0.65
    iß
    -0.65
    迎え
    -0.64
    POSITIVE LOGITS
     NFL
    2.88
     football
    2.72
     NBA
    2.42
    NFL
    2.14
     NHL
    2.09
    NBA
    1.99
     NCAA
    1.98
     Football
    1.97
     basketball
    1.96
     soccer
    1.91
    Activations Density 0.151%

    No Known Activations