© 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. 10-GEMMASCOPE-RES-131K
    7. 38730
    Prev
    Next
    INDEX
    Explanations

    legal codes and statutes

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

    The neuron detects references to legal statutes or code sections by spotting numeric citations (often with decimals) in law‐related 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
     They
    -1.81
     или
    -1.59
     with
    -1.58
     The
    -1.55
     —
    -1.48
    옅
    -1.46
    {
    -1.44
    就要
    -1.43
    badlogic
    -1.39
    OBJET
    -1.38
    POSITIVE LOGITS
    🫓
    1.86
    邽
    1.62
     emporter
    1.60
    ⅝
    1.59
    도
    1.58
     citado
    1.53
     dégustation
    1.52
    everything
    1.52
    ⢪
    1.51
    pagnole
    1.50
    Activations Density 0.018%

    No Known Activations