© 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. 110977
    Prev
    Next
    INDEX
    Explanations

    input devices: mouse, wheel, controller, steering

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

    references to computer input devices like mice, keyboards, and game controllers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    There
    -1.82
    Although
    -1.77
    While
    -1.76
    Despite
    -1.65
    Because
    -1.64
    Regardless
    -1.57
    Both
    -1.54
     them
    -1.49
    應該
    -1.48
     можуть
    -1.45
    POSITIVE LOGITS
    ︲
    2.00
    ྄
    1.90
    臜
    1.66
     recentemente
    1.57
     ܙ
    1.56
    笵
    1.55
     You
    1.52
    憮
    1.47
    OGN
    1.45
    
    1.45
    Activations Density 0.013%

    No Known Activations