© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11539
    Prev
    Next
    INDEX
    Explanations

    percent change or proportion

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

    This neuron activates on occurrences of the word “percent” (and its capitalized form “Percent”) indicating percentage units.

    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
     overarching
    -3.00
    ৢ
    -2.67
     myriad
    -2.67
     he
    -2.59
     quintessential
    -2.55
     
    -2.50
     versatility
    -2.41
     当
    -2.34
     lessen
    -2.31
    ENNA
    -2.28
    POSITIVE LOGITS
     أيض
    2.80
    獁
    2.70
    Ꮉ
    2.66
    銪
    2.58
    慙
    2.39
    providedIn
    2.38
     deri
    2.34
     現貨
    2.30
     untuk
    2.28
     イラストレーション
    2.28
    Activations Density 0.005%

    No Known Activations