© 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. 47902
    Prev
    Next
    INDEX
    Explanations

    good news

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

    The neuron strongly activates on occurrences of the adjective “good.”

    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
     uusi
    -0.96
    утбу
    -0.83
     nowy
    -0.78
    ވ
    -0.77
    âneo
    -0.74
     تحدث
    -0.74
     behoort
    -0.73
    nými
    -0.73
    categorias
    -0.72
    序列
    -0.72
    POSITIVE LOGITS
     news
    8.63
    news
    5.66
    News
    4.78
     News
    4.69
     NEWS
    4.38
    NEWS
    4.16
     noticias
    3.84
     noticia
    3.83
    ニュース
    3.80
     nieuws
    3.45
    Activations Density 0.113%

    No Known Activations