© 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. 83678
    Prev
    Next
    INDEX
    Explanations

    car mirrors

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

    The neuron strongly activates on mentions of vehicle mirrors (such as blind-spot elimination methods or mirror adjustment in cars).

    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
    mason
    -0.84
     KT
    -0.79
     mason
    -0.77
     maw
    -0.71
    Mason
    -0.71
    rodow
    -0.70
     Mason
    -0.68
     Perak
    -0.68
    idis
    -0.68
    ppens
    -0.67
    POSITIVE LOGITS
     mirrors
    2.11
     wing
    1.97
     mirror
    1.73
     Mirrors
    1.66
    Mirrors
    1.58
    mirror
    1.46
     Mirror
    1.41
    Mirror
    1.38
     side
    1.34
     gương
    1.27
    Activations Density 0.047%

    No Known Activations