© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113074
    Prev
    Next
    INDEX
    Explanations

    BPM engine

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

    references to Business Process Management (BPM) systems, workflow engines, and process automation technologies.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is keyed to occurrences of BPM and related business‐process modeling terms.

    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
     we
    -1.28
    Its
    -1.24
     eigenen
    -1.21
     the
    -1.21
    its
    -1.19
     permett
    -1.13
     ด้วย
    -1.12
     دیگر
    -1.12
     opět
    -1.10
    Such
    -1.09
    POSITIVE LOGITS
    0
    1.49
     about
    1.31
     雲
    1.30
    atge
    1.29
    ULTURE
    1.23
    Hrsg
    1.20
     hvorfor
    1.18
     confider
    1.18
    Germain
    1.17
    هایت
    1.16
    Activations Density 0.017%

    No Known Activations