© 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. 22-GEMMASCOPE-RES-131K
    7. 9465
    Prev
    Next
    INDEX
    Explanations

    terms and licenses

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

    The neuron detects formal compliance or regulatory language—terms and phrases related to obeying laws, rules, regulations, and similar legal requirements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Each
    -1.14
     potrebné
    -1.07
     for
    -1.01
     Such
    -1.01
     Done
    -0.98
     to
    -0.97
     WHY
    -0.96
    ängerin
    -0.95
    EndInit
    -0.94
    )):
    -0.93
    POSITIVE LOGITS
     both
    1.31
     rules
    1.15
     küche
    1.14
     Selamat
    1.11
     XXXIV
    1.09
     erd
    1.08
    asker
    1.07
     твои
    1.07
    TRIBUTES
    1.06
    他們
    1.05
    Activations Density 0.037%

    No Known Activations