© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74823
    Prev
    Next
    INDEX
    Explanations

    class extension and implementation

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

    The neuron activates on inheritance or extension declarations marked by the keyword “extends.”

    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
    手动
    -2.25
    ⚋
    -2.25
    籥
    -2.22
    翃
    -2.19
    姈
    -2.14
    泚
    -2.13
    ピアス
    -2.09
    荖
    -1.89
     he
    -1.88
    gimento
    -1.88
    POSITIVE LOGITS
    ’
    2.78
    鏨
    2.34
    er
    2.27
     –
    2.19
    while
    2.14
    which
    2.11
    You
    2.09
    任何
    2.00
    ments
    1.96
    MenuInflater
    1.90
    Activations Density 0.007%

    No Known Activations