© 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. 90664
    Prev
    Next
    INDEX
    Explanations

    construction machinery dealers

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

    This neuron consistently highlights tokens that are part of company or brand names (proper‐noun organization identifiers).

    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
    zość
    -0.81
    趙
    -0.77
    Cyfeiriadau
    -0.77
    bisoft
    -0.75
     Bezir
    -0.75
    槍
    -0.74
    timedia
    -0.74
     samochod
    -0.73
     Braves
    -0.73
    raham
    -0.73
    POSITIVE LOGITS
     dealer
    1.69
     dealers
    1.63
    dealer
    1.59
    Dealer
    1.49
     Dealer
    1.48
     Caterpillar
    1.42
     equipment
    1.42
     dealership
    1.33
     machine
    1.28
     machines
    1.23
    Activations Density 0.041%

    No Known Activations