© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72682
    Prev
    Next
    INDEX
    Explanations

    sequences

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

    The neuron activates whenever the text refers to the word “sequence” (including its plural form).

    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
    缯
    -2.83
     ausein
    -2.81
     gestartet
    -2.80
    を始め
    -2.69
    鑁
    -2.67
    只是一
    -2.61
    我没
    -2.58
     допомогти
    -2.55
    櫺
    -2.52
    公式サイト
    -2.39
    POSITIVE LOGITS
    哢
    3.13
    '
    3.11
    ſelves
    2.80
     stately
    2.73
    杙
    2.72
     embody
    2.70
     encourage
    2.67
     strengthen
    2.59
     your
    2.56
     adaptar
    2.53
    Activations Density 0.016%

    No Known Activations