© 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. 34-GEMMASCOPE-RES-131K
    4. 38419
    Prev
    Next
    INDEX
    Explanations

    technical syntax, legal, or blog content

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

    The neuron is primarily detecting Chinese-language character sequences.

    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
    engagent
    -0.80
    ละ
    -0.79
    ด้าน
    -0.77
     entdeckt
    -0.73
     篇
    -0.73
     Crystal
    -0.73
    rsi
    -0.70
    koon
    -0.69
    колко
    -0.69
    ริง
    -0.69
    POSITIVE LOGITS
     novels
    1.08
    novel
    1.06
     novel
    1.04
     Novel
    0.94
     Novels
    0.90
    最快更新
    0.88
     updates
    0.87
    Novel
    0.87
    峻
    0.84
     txt
    0.84
    Activations Density 0.004%

    No Known Activations