© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7866
    Prev
    Next
    INDEX
    Explanations

    twenty twenty-three

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

    This neuron detects four-digit year numbers (e.g., “2016,” “2018,” “2019”).

    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
     তখনকার
    0.71
     তৎকালীন
    0.70
    <span>
    0.68
    📠
    0.67
    in
    0.66
                   
    0.65
    okhttp
    0.65
               
    0.64
    nogo
    0.63
    
    0.63
    POSITIVE LOGITS
     पर्यंत
    0.79
    UGUST
    0.72
     iniziato
    0.68
     সালের
    0.68
     hausse
    0.68
     goles
    0.67
     lemb
    0.65
     Patrim
    0.65
     هستیم
    0.65
     WELL
    0.64
    Activations Density 0.063%

    No Known Activations