© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1272
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting four-digit numeric tokens representing years.

    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
     Tidak
    0.62
    iglie
    0.61
     คน
    0.59
     이라고
    0.59
    ம்
    0.59
     Laplacian
    0.57
    ють
    0.55
    %>%
    0.55
     Mỗi
    0.55
    ità
    0.55
    POSITIVE LOGITS
     accordance
    0.83
    ا
    0.83
     perpetuity
    0.72
    verters
    0.65
    cursion
    0.63
     lieu
    0.63
    mediately
    0.61
    很大
    0.61
    shore
    0.59
    volving
    0.58
    Activations Density 0.000%

    No Known Activations