© 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. 10-GEMMASCOPE-RES-131K
    7. 42303
    Prev
    Next
    INDEX
    Explanations

    swipe navigation and gestures

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

    The neuron activates on all forms of the word “swipe” (e.g. swipe, swipes, swiped, swiping).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    0
    -3.31
    P
    -3.02
    “
    -2.98
    ”
    -2.88
    {
    -2.80
     ‘
    -2.75
    \
    -2.75
    at
    -2.72
    S
    -2.64
    T
    -2.64
    POSITIVE LOGITS
    
    2.47
    澌
    2.44
    釙
    2.28
    很赞
    2.20
    鱨
    2.13
    讦
    2.11
    ܇
    2.11
    ᚪ
    2.09
    蕷
    2.08
    mohon
    2.06
    Activations Density 0.010%

    No Known Activations