© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19030
    Prev
    Next
    INDEX
    Explanations

    minimizing or reducing values

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

    This neuron detects occurrences of “minimize” (and its morphological variants like “minimization”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ample
    -2.80
     Would
    -2.45
    家主
    -2.39
    のいい
    -2.30
    AISSEE
    -2.30
    nobyl
    -2.27
     Where
    -2.25
    ropractic
    -2.23
     комплекс
    -2.23
    餮
    -2.22
    POSITIVE LOGITS
    You
    3.27
    觏
    2.69
    1
    2.67
    ᠁
    2.63
    Chances
    2.56
    潆
    2.55
    م
    2.52
    蟶
    2.48
    趼
    2.44
    衕
    2.42
    Activations Density 0.006%

    No Known Activations