© 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. 10-GEMMASCOPE-RES-131K
    4. 118969
    Prev
    Next
    INDEX
    Explanations

    keyboard shortcuts

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

    keyboard shortcuts and key combinations, especially those involving Ctrl or Alt modifier keys.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on parts of text describing keyboard shortcuts—modifier keys (like “Ctrl” or “Alt”) and the “+” between them.

    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
     who
    -1.70
     senaste
    -1.38
     amenaz
    -1.38
     to
    -1.37
    archiwizowane
    -1.37
    ౭
    -1.30
    őtt
    -1.30
    pompa
    -1.30
    ходил
    -1.30
     conoci
    -1.28
    POSITIVE LOGITS
     как
    1.30
     betreffende
    1.28
     one
    1.27
     diinginkan
    1.25
    หนึ่ง
    1.25
    が必要です
    1.21
     Reglamento
    1.21
     than
    1.20
     sprzedaży
    1.19
     of
    1.16
    Activations Density 0.012%

    No Known Activations