© 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. 34-GEMMASCOPE-RES-131K
    4. 54080
    Prev
    Next
    INDEX
    Explanations

    listing services after 'and'

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

    This neuron detects coordinating conjunctions that link paired items in enumerations (e.g. noun-and-noun lists).

    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
    voiture
    -0.89
     DialogInterface
    -0.81
    ʁ
    -0.79
     ทาง
    -0.79
     ponts
    -0.77
     Rios
    -0.77
     подчи
    -0.75
    aquí
    -0.75
    alen
    -0.75
     riscos
    -0.73
    POSITIVE LOGITS
     services
    2.25
     systems
    1.48
    services
    1.42
     tools
    1.41
     equipment
    1.34
     processes
    1.34
     techniques
    1.32
     components
    1.30
     materials
    1.29
     methods
    1.27
    Activations Density 0.128%

    No Known Activations