© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12422
    Prev
    Next
    INDEX
    Explanations

    visual output rendering

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

    The neuron activates on occurrences of “render” or “rendering” (and related forms like “renderer”) in document text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    y
    -3.14
     atau
    -2.97
    鯪
    -2.83
    Beberapa
    -2.58
    你的
    -2.48
     {
    -2.47
    Setelah
    -2.44
    技术
    -2.38
     bambino
    -2.38
     или
    -2.33
    POSITIVE LOGITS
     altamente
    3.02
    酲
    2.64
    瘓
    2.58
    '
    2.55
     jähr
    2.53
     
    2.47
    atire
    2.47
     Resolución
    2.42
     ܪ
    2.39
    其妙
    2.38
    Activations Density 0.007%

    No Known Activations