© 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. 80976
    Prev
    Next
    INDEX
    Explanations

    athletic events and runners

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

    The neuron is primarily detecting numeric tokens—especially years, measurements, and other numerical statistics.

    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
    ติด
    -0.80
     Yamamoto
    -0.76
     Executed
    -0.76
    bný
    -0.74
    AxisAlignment
    -0.74
    EVAL
    -0.72
    差し
    -0.72
     executed
    -0.72
     tendencias
    -0.71
    executed
    -0.70
    POSITIVE LOGITS
     running
    0.83
     Runner
    0.79
    rear
    0.77
     Running
    0.77
     metabolic
    0.75
    bursts
    0.75
    номи
    0.75
     trate
    0.74
     向け
    0.74
    runners
    0.74
    Activations Density 0.036%

    No Known Activations