© 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. 39853
    Prev
    Next
    INDEX
    Explanations

    keyboard modifiers

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

    The neuron detects mentions of keyboard modifier keys (e.g. Ctrl, Alt, Shift) in shortcut descriptions.

    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
     that
    -1.45
     in
    -1.23
     to
    -1.20
     diseñ
    -1.15
     especially
    -1.15
    nhung
    -1.09
     problems
    -1.09
     easy
    -1.05
    inière
    -1.05
    ETH
    -1.05
    POSITIVE LOGITS
    還會
    1.26
     necessario
    1.20
    還要
    1.10
     '*')
    1.05
    还需要
    1.04
    requipa
    1.01
    ဤ
    0.99
     deine
    0.99
     effectu
    0.97
    างเกง
    0.96
    Activations Density 0.014%

    No Known Activations