© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45349
    Prev
    Next
    INDEX
    Explanations

    closing brackets and quotes

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

    The neuron activates on isolated code‐style tokens that include non-alphanumeric characters or mixed capitalization—e.g. camelCase identifiers, punctuation like parentheses or hyphens.

    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
     is
    -2.50
    s
    -2.06
     adds
    -2.00
    ar
    -1.98
     introduces
    -1.97
    c
    -1.83
     expands
    -1.81
     и
    -1.80
     some
    -1.78
     був
    -1.78
    POSITIVE LOGITS
    
    2.44
    ⇴
    2.17
    
    2.13
    ípio
    2.00
    眛
    1.98
    ܊
    1.94
    
    1.90
     indicato
    1.88
    wickshire
    1.88
    鐿
    1.88
    Activations Density 0.029%

    No Known Activations