© 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. 70724
    Prev
    Next
    INDEX
    Explanations

    industry and business

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

    The neuron detects mentions of industries or businesses quantified by numbers or monetary values (e.g. “billion-dollar industry,” “big business,” “growing industry”).

    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
     the
    -1.74
     or
    -1.66
     three
    -1.40
      「
    -1.39
     increased
    -1.38
    jauh
    -1.38
    ====
    -1.38
     changes
    -1.37
     when
    -1.36
     a
    -1.35
    POSITIVE LOGITS
     علاوه
    1.52
    готовки
    1.49
    蹰
    1.43
    правки
    1.36
     neces
    1.32
    h
    1.32
     Además
    1.30
    роль
    1.28
     المعيار
    1.26
     ทำ
    1.25
    Activations Density 0.041%

    No Known Activations