© 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. 1602
    Prev
    Next
    INDEX
    Explanations

    although introducing contrast

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

    The neuron consistently activates on the concessive conjunction “although.”

    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
    镦
    -2.36
    푣
    -2.34
     แต่
    -2.33
     affez
    -2.31
    휀
    -2.27
    ⼥
    -2.23
    ﮑ
    -2.14
     speciali
    -2.14
    ꜄
    -2.11
    栊
    -2.09
    POSITIVE LOGITS
    {
    2.39
     чёр
    2.17
     —
    2.14
     it
    1.88
    ong
    1.86
     or
    1.84
    and
    1.80
    了两
    1.80
    al
    1.78
    '
    1.78
    Activations Density 0.007%

    No Known Activations