© 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. 11211
    Prev
    Next
    INDEX
    Explanations

    start or beginning

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

    The neuron is specialized to pick out numeric expressions (multi‐digit numbers, scores, times, and quantities).

    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
    近年来
    0.84
    주
    0.81
    刚才
    0.78
     BlogPost
    0.77
    middels
    0.77
     عرصے
    0.76
    >?,
    0.76
    多年
    0.75
     unenforceable
    0.74
    灿
    0.74
    POSITIVE LOGITS
     awal
    1.77
     시작
    1.60
     inicial
    1.55
    แรก
    1.55
     iniziale
    1.52
     start
    1.51
     başlayan
    1.50
    START
    1.43
     inception
    1.43
     Beginn
    1.43
    Activations Density 2.999%

    No Known Activations