© 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. 22-GEMMASCOPE-RES-131K
    7. 68661
    Prev
    Next
    INDEX
    Explanations

    button click or press

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

    The neuron fires on mentions of pressing or clicking buttons (e.g., “press,” “button,” “clicked,” “buttonPressed”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    leftarrow
    -1.10
    也是
    -0.98
    因为
    -0.93
     is
    -0.93
    ep
    -0.89
    e
    -0.88
    runner
    -0.86
    ston
    -0.86
     Usa
    -0.86
    </u>
    -0.85
    POSITIVE LOGITS
     demasi
    1.22
    ън
    1.10
     henvisninger
    1.09
     navegando
    1.09
    твра
    1.00
     Ál
    1.00
     expédié
    1.00
     apret
    0.99
     Dysfunction
    0.99
     suffisamment
    0.99
    Activations Density 0.051%

    No Known Activations