© 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. 64937
    Prev
    Next
    INDEX
    Explanations

    this recent time

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

    The neuron fires on time‐related words and phrases (like “this,” “last,” “past,” “year,” “week,” “month,” etc.) that locate events in time.

    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
     tomorrow
    -1.48
     upcoming
    -1.34
     next
    -1.24
    Tomorrow
    -1.24
     coming
    -1.20
    Coming
    -1.10
    upcoming
    -1.09
    tomorrow
    -1.09
    next
    -1.01
     Tomorrow
    -0.99
    POSITIVE LOGITS
     past
    4.44
     pasado
    3.02
    Past
    2.88
     прошлом
    2.88
    past
    2.88
     Past
    2.80
     vergangenen
    2.72
     گذشته
    2.53
     yesterday
    2.50
     прошлого
    2.48
    Activations Density 0.049%

    No Known Activations