© 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. 57296
    Prev
    Next
    INDEX
    Explanations

    mouse motion listener

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

    This neuron is specialized to detect programming code syntax (operators, punctuation, and code keywords) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    icken
    -0.82
     impairments
    -0.81
     concede
    -0.80
    Planner
    -0.77
    责任
    -0.77
    关键字
    -0.77
    ConstraintMaker
    -0.75
    monary
    -0.75
    roup
    -0.74
     Malam
    -0.72
    POSITIVE LOGITS
     sensitivity
    0.87
     Mouse
    0.85
     position
    0.83
     ∈
    0.83
     delta
    0.82
     motion
    0.82
     Delta
    0.82
     Motion
    0.81
     relative
    0.81
     Movement
    0.81
    Activations Density 0.016%

    No Known Activations