© 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. 107474
    Prev
    Next
    INDEX
    Explanations

    driving and drivers

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

    The neuron activates on the auxiliary “was” (and associated subject tokens) that signal past-tense narrative or passive-voice descriptions in reporting.

    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
     航空
    -0.81
    temon
    -0.77
    jerg
    -0.75
    xaml
    -0.75
    зовы
    -0.73
    bytecode
    -0.71
    zegorz
    -0.67
    రం
    -0.67
    acic
    -0.67
     Aircraft
    -0.67
    POSITIVE LOGITS
     driving
    6.34
     Driving
    5.13
    driving
    5.09
    Driving
    5.09
     drive
    4.34
     drives
    4.13
     drove
    4.00
     driver
    3.78
     drivers
    3.61
    drive
    3.47
    Activations Density 0.104%

    No Known Activations