© 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. 130626
    Prev
    Next
    INDEX
    Explanations

    json serialization or html tables

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

    The neuron fires on occurrences of the “Newtonsoft.Json” library name.

    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
    $
    -2.88
    </strong>
    -2.63
    =
    -2.41
    诋
    -2.41
    “
    -2.36
     --
    -2.30
    e
    -2.19
    </h4>
    -2.09
    ↵
    -2.09
    been
    -1.98
    POSITIVE LOGITS
    ୈ
    2.77
     oiseaux
    2.53
    祘
    2.42
    窳
    2.39
    諴
    2.38
    ܃
    2.33
     gustado
    2.30
    甡
    2.30
    晢
    2.28
    CurtirCurtir
    2.23
    Activations Density 0.001%

    No Known Activations