© 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. 131008
    Prev
    Next
    INDEX
    Explanations

    The neuron detects standalone parenthesis tokens (i.e. isolated “(” or “)” symbols).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    parentheses with calculations or words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     of
    -2.36
    “
    -2.27
    chränkungen
    -2.09
     to
    -2.02
    槩
    -2.00
    就已经
    -1.98
    ⟞
    -1.95
    と思いました
    -1.90
    grupos
    -1.86
    我们就
    -1.85
    POSITIVE LOGITS
    سی
    2.03
    ależ
    2.02
    section
    1.97
    銲
    1.96
     Remover
    1.94
    iranje
    1.91
    嬷
    1.88
    在大
    1.87
    癀
    1.87
    ?),
    1.85
    Activations Density 0.048%

    No Known Activations