© 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. 34-GEMMASCOPE-RES-131K
    4. 45463
    Prev
    Next
    INDEX
    Explanations

    marathon runner

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

    The neuron fires strongly on occurrences of the word “marathon” (and closely related forms).

    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
     positifs
    -0.80
    かと
    -0.77
     也
    -0.73
    基本上
    -0.72
    ukin
    -0.71
    oxidant
    -0.71
                   
    -0.70
                          
    -0.70
     soluble
    -0.69
    фра
    -0.69
    POSITIVE LOGITS
     runner
    1.61
     runners
    1.37
     Runners
    1.22
     Runner
    1.08
    Marathon
    1.03
     Marathon
    0.98
     running
    0.98
    Runner
    0.97
    Running
    0.94
    läufer
    0.91
    Activations Density 0.013%

    No Known Activations