© 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. 4307
    Prev
    Next
    INDEX
    Explanations

    swing, swinging, swung

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

    The neuron consistently activates on the word “swing” (in any context).

    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
    ıyors
    -0.90
     wander
    -0.84
    Respuesta
    -0.84
    インナー
    -0.77
    وى
    -0.75
    assertIs
    -0.74
     emphatically
    -0.72
     /(\
    -0.71
     której
    -0.71
    遊戯
    -0.71
    POSITIVE LOGITS
     Swing
    2.41
     swing
    2.39
    Swing
    2.36
    swing
    2.13
     swung
    1.99
     swinging
    1.90
     swings
    1.84
     pendulum
    1.43
    Sw
    1.15
    韆
    1.09
    Activations Density 0.008%

    No Known Activations