© 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. 34-GEMMASCOPE-RES-131K
    7. 48341
    Prev
    Next
    INDEX
    Explanations

    introduces specific topics

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

    This neuron detects JavaScript touch/gesture event names and related API identifiers (e.g. the Hammer.js event strings like “tap”, “swipeleft”, “pinch”, etc.).

    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
     gevallen
    -0.80
     Rivas
    -0.75
     luz
    -0.72
     الحق
    -0.72
    Κ
    -0.70
     ELECTRON
    -0.69
    Pier
    -0.69
     спокой
    -0.68
    द्धि
    -0.67
    Kri
    -0.67
    POSITIVE LOGITS
     pinch
    1.52
     fingers
    1.41
     gesture
    1.34
     pinching
    1.33
     finger
    1.32
     Finger
    1.23
    pinch
    1.23
     Pinch
    1.22
     swipe
    1.21
    fingers
    1.20
    Activations Density 0.039%

    No Known Activations