© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52584
    Prev
    Next
    INDEX
    Explanations

    URL closing bracketThis neuron detects URL closing brackets like `]` appearing after a URL. The most common sequence seems to be the closing of a URL structure, often indicated by `]`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    http
    0.68
     http
    0.55
     इलाहाबाद
    0.48
     xrange
    0.47
     Allahabad
    0.44
     econometric
    0.44
    corpus
    0.42
     envisaged
    0.42
     fraudulent
    0.41
    ="#{
    0.41
    POSITIVE LOGITS
    🫶
    0.77
    🤎
    0.67
    🩷
    0.67
    🤍
    0.65
     २०२
    0.64
     🥰
    0.64
     ©️
    0.63
    🥹
    0.62
     проєкту
    0.61
     SwiftUI
    0.60
    Activations Density 0.019%

    No Known Activations