© 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. 10-GEMMASCOPE-RES-131K
    7. 41527
    Prev
    Next
    INDEX
    Explanations

    vehicle license plates and views

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

    The neuron activates on mentions of “plate” in the context of vehicle license plates or plate‐reading/recognition systems.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    尛
    -1.72
    旖
    -1.72
     abiertos
    -1.68
    呖
    -1.67
    7
    -1.64
     тыся
    -1.57
    臯
    -1.56
     ſta
    -1.54
    ↵↵
    -1.54
    The
    -1.52
    POSITIVE LOGITS
     You
    1.90
    翆
    1.57
     the
    1.55
    kyt
    1.49
    ことは
    1.49
     dejan
    1.45
     Tienen
    1.43
     filho
    1.41
    炻
    1.41
    workbench
    1.38
    Activations Density 0.010%

    No Known Activations