© 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. 34-GEMMASCOPE-RES-131K
    7. 64180
    Prev
    Next
    INDEX
    Explanations

    Bugatti cars

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

    The neuron strongly activates on mentions of high‐end supercar names (especially Bugatti models like “Chiron” and “Veyron”).

    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
     bottes
    -0.66
     Nhật
    -0.65
     cos
    -0.63
     sebesar
    -0.63
     canales
    -0.62
    هاز
    -0.62
     Ashland
    -0.61
    Maxwell
    -0.61
     Senate
    -0.60
    vā
    -0.60
    POSITIVE LOGITS
     Bugatti
    1.57
     Vey
    1.39
     Chiron
    1.36
    Vey
    1.20
     EB
    1.03
    Bug
    1.01
     BUG
    1.01
    EB
    0.94
     Et
    0.92
    BUG
    0.89
    Activations Density 0.018%

    No Known Activations