© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11027
    Prev
    Next
    INDEX
    Explanations

    demographic, democratizing, demanding, demons

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

    This neuron activates on occurrences of the letter sequence “dem” within tokens.

    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
     वाटते
    0.57
    irectional
    0.57
     শুভেচ্ছা
    0.57
    anka
    0.55
     Ее
    0.54
    adoo
    0.54
     fragmentary
    0.54
    #.
    0.52
    uppercase
    0.51
    ilea
    0.51
    POSITIVE LOGITS
     Dem
    1.22
     DEM
    1.20
     демо
    1.20
    Dem
    1.20
     dem
    1.17
    dem
    1.13
     dém
    1.02
    DEM
    0.97
     Demi
    0.97
     demons
    0.95
    Activations Density 0.195%

    No Known Activations