© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85112
    Prev
    Next
    INDEX
    Explanations

    flash messages `TempData` with notice

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

    The neuron fires on occurrences of the word “flash.”

    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
     was
    -2.00
    其他
    -1.52
    j
    -1.40
    呵
    -1.38
    l
    -1.34
    <h3>
    -1.33
    </h5>
    -1.32
     bekannt
    -1.31
     velmi
    -1.30
    roffenen
    -1.30
    POSITIVE LOGITS
    сибир
    1.66
    курен
    1.55
    你这个
    1.52
    但却
    1.49
    祧
    1.43
    你这
    1.42
    flashdata
    1.38
    vação
    1.38
    鹮
    1.37
     scouring
    1.36
    Activations Density 0.002%

    No Known Activations