© 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. 74711
    Prev
    Next
    INDEX
    Explanations

    mathematical or code variables

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

    The neuron strongly activates on programming identifiers (variable, function, and other code names) in code snippets.

    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
     They
    -1.80
     ۱۵
    -1.59
     about
    -1.56
    </h5>
    -1.56
    CCER
    -1.38
     ۱۳
    -1.37
     for
    -1.34
    توضیحات
    -1.34
     so
    -1.33
     از
    -1.33
    POSITIVE LOGITS
    )
    2.06
    _
    1.82
    ająca
    1.63
     répon
    1.63
    ühnen
    1.54
     fuß
    1.52
     mêmes
    1.46
    '
    1.46
    ichteten
    1.43
     impossível
    1.43
    Activations Density 0.071%

    No Known Activations