© 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. 64578
    Prev
    Next
    INDEX
    Explanations

    in life or time

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

    This neuron detects temporal context words—like “earlier,” “development,” and “life”—that typically occur around or immediately after year/date mentions.

    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
     anything
    -1.00
    Recently
    -0.98
     beijo
    -0.98
    定休日
    -0.98
     velocità
    -0.97
     rápidos
    -0.96
     amortecedor
    -0.96
    Angebot
    -0.96
    最後に
    -0.96
     certain
    -0.95
    POSITIVE LOGITS
     proceedings
    1.20
     lifecycle
    1.00
     cycle
    0.96
    嶋
    0.94
     Lifecycle
    0.91
     day
    0.90
     season
    0.89
     chronology
    0.89
     life
    0.88
     نادي
    0.87
    Activations Density 0.023%

    No Known Activations