© 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. 15909
    Prev
    Next
    INDEX
    Explanations

    code import statements

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

    The neuron detects floating-point numeric literals (numbers with decimal points).

    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
     three
    0.70
    首先
    0.68
     two
    0.67
    三个
    0.67
    两个
    0.66
    兩個
    0.65
    最初は
    0.62
    兩
    0.61
     complicated
    0.60
    三种
    0.60
    POSITIVE LOGITS
     Lebih
    0.84
    siehe
    0.80
    ättre
    0.76
    𝘁
    0.75
     یا
    0.73
     किंवा
    0.70
     Wettbewer
    0.70
    Veja
    0.70
    镙
    0.70
     или
    0.69
    Activations Density 0.000%

    No Known Activations