© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99267
    Prev
    Next
    INDEX
    Explanations

    capacitive touch screens

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

    The neuron activates on mentions of touch‐based display technology—especially “touch,” “touchscreen,” and “capacitive” panels.

    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
    holz
    -0.81
    ousse
    -0.78
    дость
    -0.77
    burgo
    -0.73
     FERR
    -0.73
    芥
    -0.72
    dani
    -0.69
     Tempor
    -0.65
    Green
    -0.65
     向
    -0.65
    POSITIVE LOGITS
     touch
    3.42
     touchscreen
    3.20
    touch
    2.58
     Touch
    2.53
    Touch
    2.39
     TOUCH
    2.22
    タッチ
    2.20
    TOUCH
    2.11
     touches
    2.09
    触摸
    2.02
    Activations Density 0.075%

    No Known Activations