© 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. 34-GEMMASCOPE-RES-131K
    7. 103748
    Prev
    Next
    INDEX
    Explanations

    foreign place names and prefixes

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

    The neuron strongly responds to character substrings like “uk” (and related two-letter sequences such as “um” or “un”) inside tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ⇑
    -0.77
    kú
    -0.75
    /.../
    -0.74
    даго
    -0.73
     Devine
    -0.73
     چون
    -0.72
     חוק
    -0.72
    ׃
    -0.70
     ruhig
    -0.70
     musique
    -0.70
    POSITIVE LOGITS
    ZJ
    0.76
     précédemment
    0.76
    وائد
    0.76
    そこ
    0.75
    veland
    0.74
    于是
    0.74
    veston
    0.73
    polis
    0.73
    ogie
    0.72
    Sådan
    0.72
    Activations Density 0.052%

    No Known Activations