© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9955
    Prev
    Next
    INDEX
    Explanations

    de + noun

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

    This neuron responds to the Romance‐language preposition “de” (and its forms “du,” “d’,” etc.) as it appears in names and titles.

    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
    Bibliography
    0.72
    附
    0.70
    ├
    0.68
    -
    0.64
    DateTimePicker
    0.64
    redient
    0.62
    RECEIVED
    0.61
    ly
    0.61
    ู
    0.61
    Package
    0.60
    POSITIVE LOGITS
     manière
    1.13
     riferimento
    1.10
     către
    1.07
     referencia
    1.05
     lancio
    1.04
     vocês
    1.03
     maneira
    1.03
     referência
    1.03
     référence
    1.02
     acordo
    1.01
    Activations Density 0.062%

    No Known Activations