© 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. 9912
    Prev
    Next
    INDEX
    Explanations

    reducing or decreasing something

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

    The neuron is triggered by mentions of reducing or reduction (e.g. “reduce,” “reducing,” “reduction,” “reduces”).

    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
     увеличения
    0.68
     cleanliness
    0.62
     увеличение
    0.60
    싼
    0.60
     cheaply
    0.59
     PERFORMANCE
    0.59
     upregulation
    0.59
    刧
    0.59
    rains
    0.58
    лган
    0.57
    POSITIVE LOGITS
     thiểu
    1.12
     Reduce
    1.08
     reduce
    1.07
     reduces
    1.05
     reduziert
    1.03
     redu
    1.02
     giảm
    1.02
    ลด
    1.01
    reduce
    1.00
     Reducing
    1.00
    Activations Density 0.309%

    No Known Activations