© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4632
    Prev
    Next
    INDEX
    Explanations

    specific day or time

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

    The neuron fires on temporal markers, especially words like “Today” and explicit date references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    ক
    1.04
    AN
    1.00
    ς
    0.96
     hereto
    0.92
    тавли
    0.91
    ATG
    0.89
    ES
    0.89
    到时候
    0.84
    > </
    0.84
    不久
    0.84
    POSITIVE LOGITS
    ীবন
    1.02
    ться
    0.97
     vandaag
    0.96
     pomeriggio
    0.91
     morgen
    0.89
    itä
    0.88
    面的
    0.87
    ন্ম
    0.86
    ක්ෂ
    0.86
    ्ञ
    0.85
    Activations Density 0.084%

    No Known Activations