© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115826
    Prev
    Next
    INDEX
    Explanations

    swipe gestures

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

    The neuron strongly activates on any mention of “swipe” (and its variants) indicating a swipe gesture or action.

    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
    Ethio
    -0.84
    鏌
    -0.81
    Tabela
    -0.76
    GROUND
    -0.75
     reproducción
    -0.74
     Syr
    -0.74
    注射
    -0.73
    postdata
    -0.73
     Wastewater
    -0.72
    Scheduled
    -0.72
    POSITIVE LOGITS
     swipe
    3.02
    Swipe
    2.31
     Swipe
    2.28
    swipe
    2.27
     slide
    1.70
     slides
    1.63
     sliding
    1.55
     slid
    1.53
     Slide
    1.52
     sw
    1.42
    Activations Density 0.030%

    No Known Activations