© 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. 34-GEMMASCOPE-RES-131K
    7. 50105
    Prev
    Next
    INDEX
    Explanations

    pipeline and pipe mentions

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

    The neuron is specialized to detect mentions of major pipeline names or pipeline projects (e.g. “TransCanada Pipelines,” “Keystone XL Pipeline”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     peccato
    -0.81
    Domains
    -0.77
     tired
    -0.75
     medical
    -0.69
    Redacción
    -0.69
    สน
    -0.68
     domani
    -0.67
     esternos
    -0.65
     ziekte
    -0.65
    Francesca
    -0.64
    POSITIVE LOGITS
     pipeline
    3.05
     pipelines
    2.45
     Pipeline
    2.44
    pipeline
    2.28
    Pipeline
    2.20
     Pip
    1.95
     pipe
    1.95
     pip
    1.85
    pipe
    1.81
    Pip
    1.71
    Activations Density 0.027%

    No Known Activations