© 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. 34876
    Prev
    Next
    INDEX
    Explanations

    run or runs followed by a preposition

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

    The neuron detects occurrences of the verb “run” (in its various forms) in text.

    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
    bernador
    -1.05
    因為
    -0.97
    會有
    -0.93
     arşivlendi
    -0.91
     vestiti
    -0.88
    kelt
    -0.88
    因为
    -0.87
    過了
    -0.86
    cepatan
    -0.85
    styp
    -0.85
    POSITIVE LOGITS
     errands
    2.28
     gamut
    1.66
     running
    1.55
     Running
    1.55
     run
    1.45
    Running
    1.44
     ran
    1.41
     interference
    1.39
     amo
    1.37
     parallel
    1.34
    Activations Density 0.048%

    No Known Activations