© 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. 31991
    Prev
    Next
    INDEX
    Explanations

    days and time references

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

    This neuron detects date-related tokens (e.g. day‐of‐week names, month names, and numeric day/month values).

    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
     منذ
    -0.81
    ầ
    -0.75
    sodik
    -0.73
     comun
    -0.70
    楼主
    -0.68
     prepping
    -0.68
     polska
    -0.67
     Præ
    -0.67
    зывали
    -0.66
     Marac
    -0.66
    POSITIVE LOGITS
     past
    1.16
     dernier
    1.16
     next
    1.14
     last
    1.03
     current
    1.00
     upcoming
    0.99
     forthcoming
    0.94
     LAST
    0.93
     الماضي
    0.93
     pasado
    0.88
    Activations Density 0.018%

    No Known Activations