© 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. 10008
    Prev
    Next
    INDEX
    Explanations

    code delimiters or structures

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

    The main thing this neuron does is detect numerical quantities (especially decimals and other number tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    commas in product listings or structured data entries.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    boilerplate e-commerce/product listing text that states where items are most popular and details regional supply/distribution information.

    oai_token-act-pair · gpt-5Triggered 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
    🦦
    0.73
    斛
    0.73
    味的
    0.72
    ुकी
    0.70
    ivy
    0.70
    håll
    0.70
    𝙛
    0.69
     Datas
    0.68
    aS
    0.67
    શો
    0.65
    POSITIVE LOGITS
     может
    0.95
     temat
    0.91
     chiều
    0.90
     Может
    0.86
     слегка
    0.86
     creación
    0.84
     ткань
    0.82
     चर्चित
    0.80
     espirit
    0.80
     maio
    0.79
    Activations Density 0.001%

    No Known Activations