© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25729
    Prev
    Next
    INDEX
    Explanations

    granting permission to any person

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

    This neuron detects the “to any person” phrase (the licensing grant clause) as in “Permission is hereby granted… to any person obtaining a copy…”

    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
    Owners
    -0.71
    Hands
    -0.71
     kard
    -0.69
    afe
    -0.69
    خی
    -0.68
    rica
    -0.67
    zeichneten
    -0.66
    Luxembourg
    -0.66
     Luxembourg
    -0.66
     gagne
    -0.66
    POSITIVE LOGITS
     население
    0.72
    ustes
    0.69
    wige
    0.65
    Blessings
    0.63
     Commence
    0.62
    墾
    0.62
    ribue
    0.61
     waivers
    0.60
     Bischof
    0.60
     angeb
    0.60
    Activations Density 0.109%

    No Known Activations