© 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. 115456
    Prev
    Next
    INDEX
    Explanations

    types of law

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

    The neuron flags occurrences of legal terms or references to laws and legal contexts.

    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
    اعر
    -0.78
     temer
    -0.73
    Consigli
    -0.70
     tutu
    -0.69
     Lacrosse
    -0.69
     Cables
    -0.68
    decode
    -0.68
    Staking
    -0.68
     Safer
    -0.67
    альные
    -0.67
    POSITIVE LOGITS
     law
    2.41
     laws
    1.62
    law
    1.35
     LAW
    1.30
     Law
    1.30
     luật
    1.24
     القانون
    1.16
     international
    1.15
    Law
    1.14
     hukum
    1.09
    Activations Density 0.046%

    No Known Activations