© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2830
    Prev
    Next
    INDEX
    Explanations

    trackpad and pointing devices

    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
    ্ল
    -0.86
     sella
    -0.78
     alimente
    -0.75
     Crian
    -0.75
    БК
    -0.74
     THRO
    -0.73
     winter
    -0.73
    paramref
    -0.72
    damento
    -0.72
     Industria
    -0.71
    POSITIVE LOGITS
     touchpad
    1.62
     track
    1.35
     Track
    1.23
     pad
    1.13
    pad
    1.02
    Track
    0.98
     Pad
    0.94
     Syna
    0.93
     pointing
    0.93
     Tracks
    0.90
    Activations Density 0.041%

    No Known Activations