© 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. 1861
    Prev
    Next
    INDEX
    Explanations

    keyboard key presses

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

    The neuron flags mentions of keyboard “key” or “keys” (i.e., references to specific key presses or key-related events).

    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
     and
    -1.93
    ’
    -1.87
     dokun
    -1.59
    谷川
    -1.53
    .
    -1.48
     отдых
    -1.43
    ’，
    -1.41
     because
    -1.40
    ↵
    -1.40
     of
    -1.38
    POSITIVE LOGITS
     ส์
    2.42
    咴
    2.00
    ⎆
    1.88
    釭
    1.88
    
    1.84
    鮠
    1.84
    ৢ
    1.80
    檮
    1.79
    鸲
    1.75
    䜣
    1.74
    Activations Density 0.009%

    No Known Activations