© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32042
    Prev
    Next
    INDEX
    Explanations

    performance car models

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

    The neuron specifically activates on mentions of the “Veloster N” car model.

    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
     sank
    -0.73
    чна
    -0.71
     explorers
    -0.70
     Johansen
    -0.69
    vang
    -0.69
    憊
    -0.68
    提问
    -0.67
     grapes
    -0.66
    Confusion
    -0.66
     jeep
    -0.65
    POSITIVE LOGITS
     Golf
    1.21
     TCR
    1.09
    Golf
    0.99
     Civic
    0.96
     GTI
    0.93
    golf
    0.91
     hot
    0.87
    Civic
    0.86
    hot
    0.82
     GOLF
    0.82
    Activations Density 0.014%

    No Known Activations