© 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. 37816
    Prev
    Next
    INDEX
    Explanations

    checked out

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

    The neuron activates on phrasing around checking in or out (e.g. “checked out,” “check-in date,” “check-out date,” “late check-in/out”).

    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
    entrer
    -0.85
    DispatchQueue
    -0.85
    ánky
    -0.81
    ximos
    -0.80
    inė
    -0.79
    entrée
    -0.78
     Dm
    -0.75
     Enroll
    -0.73
    穿搭
    -0.72
    onStart
    -0.71
    POSITIVE LOGITS
     checkout
    3.55
     Checkout
    2.66
    checkout
    2.66
    Checkout
    2.55
     departure
    2.02
    checkOut
    1.79
     vacate
    1.76
     departing
    1.69
     depart
    1.62
     check
    1.58
    Activations Density 0.010%

    No Known Activations