© 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. 89828
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and codes

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

    This neuron detects words that appear in formal competition titles—especially championship-related terms.

    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
     already
    -0.83
    五
    -0.82
     five
    -0.81
     пяти
    -0.76
    According
    -0.75
     fifty
    -0.75
     according
    -0.75
     す
    -0.74
     through
    -0.73
     accepted
    -0.72
    POSITIVE LOGITS
     tetrachloride
    0.81
    Promotions
    0.80
    тельству
    0.79
     דער
    0.79
     WebDriver
    0.78
     juger
    0.77
    ('../../../
    0.77
    ícias
    0.75
     tewas
    0.75
     ($.
    0.75
    Activations Density 0.003%

    No Known Activations