© 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. 22-GEMMASCOPE-RES-131K
    7. 95332
    Prev
    Next
    INDEX
    Explanations

    mouse coordinates and movement

    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_22/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
     vienas
    -1.02
    laken
    -1.01
    蜴
    -0.97
    PAN
    -0.94
    ⚙
    -0.90
    employees
    -0.90
    |)
    -0.90
     نفس
    -0.89
     dabar
    -0.88
    %)$
    -0.87
    POSITIVE LOGITS
     aktivi
    1.05
     위치
    1.01
    瞟
    1.00
     OUTSIDE
    0.98
    ÁRIO
    0.97
    ҷ
    0.95
    シック
    0.94
    Médaille
    0.94
    iding
    0.93
     därför
    0.92
    Activations Density 0.005%

    No Known Activations