© 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. 45348
    Prev
    Next
    INDEX
    Explanations

    closing bracket

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

    The neuron fires on bracketed numeric citations or reference markers (e.g. “[1]”) in the text.

    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
    {
    -2.14
     was
    -2.11
    .
    -1.81
    躂
    -1.81
    越來
    -1.80
     Other
    -1.78
    Seguir
    -1.65
     with
    -1.63
    帶來
    -1.59
     gebouw
    -1.58
    POSITIVE LOGITS
    COLOG
    1.80
    accharides
    1.77
     siè
    1.71
     categor
    1.66
     évalu
    1.65
    쁩
    1.64
     herhangi
    1.63
     inconce
    1.61
    蚕
    1.60
     当
    1.56
    Activations Density 0.026%

    No Known Activations