© 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. 11700
    Prev
    Next
    INDEX
    Explanations

    x y coordinates

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

    The neuron specializes in spotting numeric values—especially floating‐point numbers (e.g. “X 1107.9385”).

    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
     және
    0.66
    궈
    0.63
     mög
    0.62
     uniquement
    0.59
     합니다
    0.58
     недели
    0.58
    :
    0.57
    as
    0.56
    ႇ
    0.56
    锛
    0.56
    POSITIVE LOGITS
     خان
    0.70
    óf
    0.65
     क्रिया
    0.64
     Estadística
    0.63
     कर्फ्यू
    0.62
    觫
    0.61
     قيمة
    0.61
    ibilités
    0.61
    の変化
    0.60
     CON
    0.59
    Activations Density 0.000%

    No Known Activations