© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13809
    Prev
    Next
    INDEX
    Explanations

    The neuron activates strongly on date and time expressions (e.g. month names and associated numeric day/year tokens).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     July
    1.13
    July
    1.11
     july
    1.05
     जुलाई
    1.05
     JULY
    1.05
     июле
    1.04
     夏
    1.03
    夏の
    1.03
     August
    1.00
     জুলাই
    1.00
    POSITIVE LOGITS
     Feb
    2.33
    Feb
    2.27
     February
    2.20
    February
    2.19
     FEBRUARY
    2.05
    feb
    2.03
     फरवरी
    2.02
     февра
    2.00
     Februar
    1.93
     february
    1.90
    Activations Density 0.310%

    No Known Activations