© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7023
    Prev
    Next
    INDEX
    Explanations

    license and agreements

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

    The neuron detects occurrences of legal licensing terminology (e.g., “License,” “licensed,” “Terms,” “Agreement,” “GPL,” “Unported”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    n
    0.75
    s
    0.71
     derin
    0.68
    gerufen
    0.64
    stacks
    0.64
     correg
    0.64
    nore
    0.64
    f
    0.64
    idays
    0.63
     dramat
    0.63
    POSITIVE LOGITS
     smlou
    1.01
     agreements
    1.00
     договору
    0.98
     agreement
    0.95
    契約
    0.95
    Agreement
    0.94
     договора
    0.93
     ஒப்பந்த
    0.91
     perjanjian
    0.91
     Agreements
    0.90
    Activations Density 0.084%

    No Known Activations