© 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. 22-GEMMASCOPE-RES-131K
    7. 13585
    Prev
    Next
    INDEX
    Explanations

    dates and times in articles

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

    The neuron strongly activates on the vertical bar character (“|”) used as a field or timestamp separator in article metadata lines.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     it
    -1.22
     ilustracji
    -1.03
     wciąż
    -1.02
     sababu
    -1.02
     kufanya
    -1.00
    就去
    -1.00
     will
    -0.99
     umgekehrt
    -0.98
     isang
    -0.96
     maisha
    -0.96
    POSITIVE LOGITS
     mineures
    1.18
    änderung
    1.16
     charité
    1.10
    empted
    1.09
    ÃO
    1.07
    wanderung
    1.05
    吡
    1.05
     jadx
    1.05
    paravant
    1.04
    wohnung
    1.03
    Activations Density 0.077%

    No Known Activations