© 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. 334
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on the definite article “the.”

    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
    AM
    0.41
    T
    0.41
    の
    0.39
    UL
    0.39
    C
    0.38
    W
    0.38
    ON
    0.38
    AR
    0.38
    P
    0.38
     Chỉ
    0.37
    POSITIVE LOGITS
     desired
    0.61
     entire
    0.57
     requisite
    0.56
     wearer
    0.55
     resultant
    0.53
     underlying
    0.52
     interstices
    0.52
     workpiece
    0.51
     needful
    0.51
     same
    0.50
    Activations Density 1.831%

    No Known Activations