© 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. 221
    Prev
    Next
    INDEX
    Explanations

    list items

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

    The neuron strongly activates on the substring “LED,” especially when it appears as part of hyphenated terms like “Micro‐LED.”

    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
    प्टेंबर
    0.33
     extravaganza
    0.33
     empezar
    0.32
     peruse
    0.32
    闗
    0.32
     ganar
    0.32
     decreed
    0.31
     bloggers
    0.31
     ainfi
    0.31
    开设
    0.31
    POSITIVE LOGITS
    <unused63>
    0.29
    、
    0.28
    。
    0.28
    WithSize
    0.27
    が
    0.27
     Punishment
    0.27
     Bundle
    0.27
    .
    0.27
     Subtle
    0.26
     Containing
    0.26
    Activations Density 0.056%

    No Known Activations