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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70301
    Prev
    Next
    INDEX
    Explanations

    laws and regulations

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

    The neuron is specialized in detecting mentions of laws, bills, legal drafts, or legislative acts.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     пане
    -0.77
    Sheets
    -0.75
     nơi
    -0.74
     확인
    -0.73
     CONSERV
    -0.72
    hell
    -0.71
    ﻮ
    -0.69
     mộ
    -0.69
    พี่
    -0.68
     tía
    -0.68
    POSITIVE LOGITS
     law
    3.36
     Law
    3.27
     laws
    2.69
    Law
    2.63
     Laws
    2.11
     LAW
    2.11
    law
    2.06
     قانون
    1.85
     закона
    1.75
    LAW
    1.73
    Activations Density 0.036%

    No Known Activations