© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15026
    Prev
    Next
    INDEX
    Explanations

    text explanations

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

    The neuron activates on decimal numbers (floating‐point numeric values) in the text.

    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
     สำหรับ
    0.92
     และ
    0.87
    ミルク
    0.81
     pemeriksaan
    0.80
     Более
    0.80
     ใน
    0.80
     ตาม
    0.79
     แ
    0.77
     に
    0.77
     அணுக
    0.77
    POSITIVE LOGITS
    зна
    0.79
    bsch
    0.76
    robespierre
    0.70
    绰
    0.70
    stride
    0.68
    ঞ্চ
    0.67
    tDBOutput
    0.67
    zsche
    0.66
    娼
    0.66
    綽
    0.65
    Activations Density 0.000%

    No Known Activations