© 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. 75658
    Prev
    Next
    INDEX
    Explanations

    during normal business hours

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

    The neuron detects explicit time or duration expressions (numeric timestamps, hours, minutes, “during,” etc.).

    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
     Reina
    -0.92
     ating
    -0.81
     dramat
    -0.77
     CPM
    -0.76
     AppCompatTheme
    -0.76
    vra
    -0.75
     SUBJECT
    -0.75
    entia
    -0.74
     Kro
    -0.73
    少爷
    -0.73
    POSITIVE LOGITS
     office
    2.88
     hours
    2.23
    office
    2.14
    Office
    1.93
     normal
    1.91
     Office
    1.91
     business
    1.84
     Hours
    1.76
     working
    1.73
    Hours
    1.68
    Activations Density 0.027%

    No Known Activations