© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15296
    Prev
    Next
    INDEX
    Explanations

    years ending in 2020-2024

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

    The neuron strongly activates on numeric tokens representing specific years (i.e. date/year values).

    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
     Co
    0.67
     Protection
    0.66
     S
    0.64
     K
    0.63
     Poder
    0.62
     Crear
    0.61
     выбра
    0.60
     Pendant
    0.59
     Má
    0.59
     enthalten
    0.59
    POSITIVE LOGITS
    NST
    0.81
    Τ
    0.81
    clarinet
    0.75
    我
    0.75
    NK
    0.74
    Hello
    0.73
    NBA
    0.73
    우
    0.72
    念
    0.72
    彗
    0.72
    Activations Density 0.017%

    No Known Activations