© 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. 33673
    Prev
    Next
    INDEX
    Explanations

    luxury cars and brands

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

    The neuron activates on mentions of cars, driving, and related automotive terms (e.g. sports car, Mercedes, Ferrari, driving).

    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
     SNCF
    -0.78
    chân
    -0.77
     Fahrzeug
    -0.74
     piaggio
    -0.74
     shimano
    -0.71
     übertragen
    -0.71
    車両
    -0.70
    還能
    -0.68
     Doña
    -0.68
     Hiper
    -0.67
    POSITIVE LOGITS
     cars
    1.55
     luxury
    1.55
     Ferrari
    1.45
    Ferrari
    1.31
     expensive
    1.28
     Range
    1.21
     Rolls
    1.20
     Mercedes
    1.20
     sports
    1.18
     Lamborghini
    1.16
    Activations Density 0.032%

    No Known Activations