© 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. 34-GEMMASCOPE-RES-131K
    7. 106358
    Prev
    Next
    INDEX
    Explanations

    pemberian PE

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

    The neuron specializes in spotting formal legislative references—titles, statute numbers, section citations, and other legal‐Act terminology.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    gangss
    -0.89
     titulares
    -0.84
     Tanah
    -0.81
     FACTS
    -0.77
     trầm
    -0.76
    idespread
    -0.74
    خط
    -0.73
    łbym
    -0.73
     Moulin
    -0.72
     Rajput
    -0.72
    POSITIVE LOGITS
     grant
    1.03
     Grant
    0.93
     England
    0.85
     LG
    0.84
     settlement
    0.79
    settle
    0.79
     LGA
    0.78
     invite
    0.76
     Whitehall
    0.75
    settlement
    0.73
    Activations Density 0.020%

    No Known Activations