© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14111
    Prev
    Next
    INDEX
    Explanations

    award or recognition

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

    This neuron detects mentions of award or event details—especially the dates, locations, and organizing bodies (e.g. “at the Book Expo in June,” “nominated … by the Publishers Marketing Association,” “at INternational MARINE Summit,” 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_22/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
    还不错
    -1.08
    太多
    -0.97
    Fortunately
    -0.96
    nera
    -0.94
     پیشن
    -0.93
    moil
    -0.89
     dañ
    -0.89
    Luckily
    -0.88
    hasia
    -0.87
     toiture
    -0.87
    POSITIVE LOGITS
     this
    1.13
     "";
    0.98
     recognition
    0.98
     overall
    0.97
    VCR
    0.96
     throughout
    0.96
     based
    0.96
     during
    0.95
     pamię
    0.95
    igerung
    0.95
    Activations Density 0.038%

    No Known Activations