© 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. 120021
    Prev
    Next
    INDEX
    Explanations

    Patent document identifiers

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

    The neuron detects the colons used as structural labels (e.g. in figure, table, or section headings).

    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
     always
    -1.70
    2
    -1.52
     dezelfde
    -1.52
     merely
    -1.51
     Vielfalt
    -1.49
     presumably
    -1.47
     Atmosphäre
    -1.47
    }{
    -1.44
     necessarily
    -1.43
     Vielzahl
    -1.41
    POSITIVE LOGITS
     ۱۱
    1.86
     ۱۰
    1.84
     ۱۵
    1.80
     ۳۰
    1.69
     ۱۲
    1.58
     وطن
    1.56
     unut
    1.53
    genodigd
    1.53
    Krankheitsbild
    1.52
     harte
    1.51
    Activations Density 0.001%

    No Known Activations