© 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. 59419
    Prev
    Next
    INDEX
    Explanations

    getting out of a vehicle

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

    This neuron detects instances of the phrase “get out of” (often describing exiting a vehicle).

    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
     Sonata
    -0.81
     Ibero
    -0.74
    thief
    -0.72
    няка
    -0.71
    BACK
    -0.71
    initions
    -0.71
     запуска
    -0.71
    ۦ
    -0.71
     berangkat
    -0.71
     headband
    -0.70
    POSITIVE LOGITS
     disemb
    2.30
    下車
    2.20
     exit
    1.85
     exited
    1.79
    降り
    1.77
     alight
    1.65
     выйти
    1.59
     Exit
    1.56
     exiting
    1.52
     desembar
    1.51
    Activations Density 0.024%

    No Known Activations