© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14200
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by common connectors

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

    The neuron primarily detects parentheses (especially the “(” token) 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_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
     by
    -1.17
     in
    -1.13
     at
    -1.12
     with
    -0.93
     for
    -0.93
     on
    -0.92
     a
    -0.90
     浴室
    -0.90
     one
    -0.90
     four
    -0.89
    POSITIVE LOGITS
     nhưng
    1.16
     but
    1.09
    composición
    1.00
    Indien
    0.98
    乁
    0.97
     黄色
    0.96
    unuz
    0.96
     biedt
    0.96
     utilizzati
    0.95
     riemp
    0.95
    Activations Density 0.094%

    No Known Activations