© 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. 81732
    Prev
    Next
    INDEX
    Explanations

    competition entries or submissions

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

    The neuron is tuned to detect contest or competition announcements—specifically words and phrases that call for submissions (e.g. “competition,” “calling for,” “submit,” “entries,” etc.).

    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
     Colo
    -0.74
     cập
    -0.73
    onde
    -0.73
     S
    -0.73
    jsdelivr
    -0.71
    価
    -0.70
    ="@+
    -0.70
     IM
    -0.69
     V
    -0.69
     Available
    -0.67
    POSITIVE LOGITS
     entries
    4.22
     submissions
    3.52
     Entries
    3.48
    Entries
    3.47
    entries
    3.44
     submission
    3.31
     entry
    3.27
     submitted
    3.14
     entrants
    3.08
    Entry
    2.89
    Activations Density 0.089%

    No Known Activations