© 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. 82857
    Prev
    Next
    INDEX
    Explanations

    news

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    lorette
    -0.94
    garmin
    -0.80
    ář
    -0.77
    утбу
    -0.76
    kowej
    -0.75
    nému
    -0.75
     uusi
    -0.74
    ʉ
    -0.73
     Nomination
    -0.73
     canvas
    -0.73
    POSITIVE LOGITS
     news
    4.69
     News
    3.73
    news
    3.67
    News
    3.67
     NEWS
    3.09
    NEWS
    2.88
    新闻
    2.69
     newspaper
    2.45
    ニュース
    2.31
     noticias
    2.27
    Activations Density 0.030%

    No Known Activations