© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33390
    Prev
    Next
    INDEX
    Explanations

    parentheses or quotes

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

    The neuron detects parenthetical expressions (text enclosed in 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_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
     momentous
    -1.23
     mediocre
    -1.15
     myriad
    -1.08
     acheter
    -1.07
     effectuer
    -1.05
     choisir
    -1.00
     éviter
    -1.00
     créer
    -0.98
     และ
    -0.96
     appliquer
    -0.96
    POSITIVE LOGITS
     with
    1.25
     in
    1.16
     or
    1.15
     when
    1.13
     where
    1.08
     on
    1.07
     because
    1.05
     after
    0.99
     giving
    0.93
     for
    0.93
    Activations Density 0.039%

    No Known Activations