© 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. 41797
    Prev
    Next
    INDEX
    Explanations

    any or arbitrary

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

    The neuron responds to parenthetical expressions—i.e. tokens marking or appearing inside parentheses.

    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
     inglesa
    -1.54
     …..
    -1.43
     ¨
    -1.38
     certainement
    -1.37
     
    -1.35
     vraiment
    -1.34
     !!!!
    -1.34
    
    -1.34
     BAD
    -1.31
     véritable
    -1.30
    POSITIVE LOGITS
    Many
    1.70
     on
    1.70
     many
    1.66
     at
    1.63
     Many
    1.55
     any
    1.48
     from
    1.47
     after
    1.39
     will
    1.38
     under
    1.38
    Activations Density 0.088%

    No Known Activations