© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9549
    Prev
    Next
    INDEX
    Explanations

    start or end of period

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

    The neuron activates on the phrase “of each” when used in recurring time expressions (e.g. “end of each month,” “start of each year”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    phrases indicating the start of a time period (beginning/end/start of each month/semester/year/cycle).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    phrases that mark temporal boundaries—references to the beginning or end of a scheduled period, cycle, or interval.

    oai_token-act-pair · gpt-5Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     naszej
    0.63
     questa
    0.62
     pořád
    0.61
     நான்கு
    0.61
     melanin
    0.60
    ונת
    0.60
     venture
    0.59
     пять
    0.59
     infinitesimal
    0.58
     naciones
    0.57
    POSITIVE LOGITS
    ையுடன்
    0.63
     successivo
    0.56
     preceding
    0.55
    zoni
    0.52
    டன்
    0.51
    bodyParser
    0.51
    クロン
    0.51
     berikutnya
    0.51
    gewicht
    0.50
    依
    0.50
    Activations Density 0.001%

    No Known Activations