© 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. 10-GEMMASCOPE-RES-131K
    4. 41945
    Prev
    Next
    INDEX
    Explanations

    hostname, 对话框, 行为, orghini, Playing, asset

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

    The neuron responds to occurrences of the Chinese copular verb “是” used in defining or descriptive phrases.

    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
    s
    -2.86
    ico
    -2.61
     unſ
    -2.55
    有
    -2.53
    the
    -2.52
     "
    -2.45
    How
    -2.45
    有個
    -2.44
    ته
    -2.38
    在
    -2.38
    POSITIVE LOGITS
     This
    2.78
     “
    2.63
     navide
    2.55
     Which
    2.52
     Then
    2.38
     According
    2.31
     diagnostica
    2.30
     fã
    2.30
     We
    2.27
     genaue
    2.23
    Activations Density 0.000%

    No Known Activations