© 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. 5085
    Prev
    Next
    INDEX
    Explanations

    Wikipedia pages and structured content

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

    The neuron is triggered by capitalized proper names—especially brand, product, or section titles.

    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
    /
    0.48
    ąd
    0.44
    ombrie
    0.44
    ategoria
    0.43
     желательно
    0.43
    быз
    0.43
     করছি
    0.42
    hmad
    0.42
     mellett
    0.42
     عباره
    0.41
    POSITIVE LOGITS
     prokary
    0.47
     ①
    0.44
    Wik
    0.42
    \|
    0.41
     Wik
    0.41
    那些
    0.40
     wik
    0.40
     Page
    0.40
    什么
    0.38
     நீ
    0.38
    Activations Density 0.069%

    No Known Activations