© 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. 12017
    Prev
    Next
    INDEX
    Explanations

    inflation: economic problems

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

    This neuron primarily detects noun forms ending in “-ation.”

    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
     FCC
    0.58
    PSY
    0.57
    રસ
    0.54
    琼
    0.53
     Menge
    0.53
     scre
    0.52
     McCoy
    0.52
     PSY
    0.52
    龌
    0.52
    uther
    0.51
    POSITIVE LOGITS
     Infl
    2.09
     Inflammation
    2.05
    Infl
    2.03
     inflammation
    2.00
    inflammation
    1.99
     inflammatory
    1.96
     inflam
    1.91
     inflamm
    1.89
     infl
    1.88
     inflation
    1.87
    Activations Density 0.140%

    No Known Activations