© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100548
    Prev
    Next
    INDEX
    Explanations

    broadcasting television or radio

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

    The neuron fires on words that denote broadcasting or airing of a show (e.g., “broadcast,” “aired,” “broadcasts”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    躄
    -2.02
     في
    -1.82
    ediakan
    -1.77
    翼翼
    -1.76
    missão
    -1.75
    探し
    -1.73
    ᠂
    -1.70
     الفلسط
    -1.70
     маленьких
    -1.69
     atau
    -1.68
    POSITIVE LOGITS
    
    2.05
     строительство
    1.72
     тысячи
    1.71
     aprobó
    1.71
    鼴
    1.70
    banez
    1.68
    廨
    1.66
     laterales
    1.66
    锖
    1.65
     improbable
    1.63
    Activations Density 0.034%

    No Known Activations