© 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-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 464
    Prev
    Next
    INDEX
    Explanations

    The neuron is a detector for formal “legalese” or contract‐style wording (e.g. terms like “Agreement,” “provision,” “jurisdiction,” “shall,” “invalid,” etc.).

    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_31_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
    xyplot
    0.45
    MyToolkit
    0.44
    🔭
    0.43
     mottled
    0.42
     silice
    0.42
     diaphrag
    0.41
     emble
    0.40
     періо
    0.40
     पूर्वानु
    0.39
     வித்திய
    0.39
    POSITIVE LOGITS
     
    0.40
      
    0.39
     a
    0.36
    i
    0.36
    u
    0.36
    init
    0.35
    //
    0.35
    is
    0.34
    ਨ
    0.34
       
    0.34
    Activations Density 0.097%

    No Known Activations