© 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. 10-GEMMASCOPE-RES-131K
    7. 59779
    Prev
    Next
    INDEX
    Explanations

    around, about, hand

    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_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
    久しぶり
    -2.13
     люди
    -1.99
    なかな
    -1.88
    楽しかった
    -1.88
     oggi
    -1.81
    谖
    -1.80
     dziś
    -1.80
    为什么会
    -1.77
    圪
    -1.73
    
    -1.72
    POSITIVE LOGITS
     in
    2.31
     for
    2.05
    '
    1.75
     to
    1.70
    ant
    1.62
    »;
    1.62
    }
    1.61
    😣
    1.60
    😐
    1.59
    🤭
    1.59
    Activations Density 0.004%

    No Known Activations