© 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. 2285
    Prev
    Next
    INDEX
    Explanations

    **late and early periods**

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

    The neuron activates on numerical tokens representing historical years or dates.

    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
     giúp
    0.86
     номера
    0.65
     nghiệm
    0.64
     pourcentage
    0.63
     весь
    0.61
     celý
    0.61
     哦
    0.61
     всіх
    0.61
     окна
    0.60
     énorme
    0.60
    POSITIVE LOGITS
    公元
    0.77
     القرن
    0.65
     siglo
    0.64
    紀
    0.63
     decades
    0.61
     millennia
    0.59
     eighties
    0.58
    ⴷ
    0.58
     eighteenth
    0.57
     xii
    0.57
    Activations Density 0.027%

    No Known Activations