© 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. 13617
    Prev
    Next
    INDEX
    Explanations

    method calls and event handlers

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

    The neuron activates on identifier tokens that serve as formal parameters or arguments in function and callback signatures across different programming languages.

    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
     geforce
    -1.63
     tasche
    -1.55
     meras
    -1.54
     magasiner
    -1.54
     tempel
    -1.52
     of
    -1.51
     plis
    -1.50
     chofe
    -1.48
     sosi
    -1.47
     brune
    -1.46
    POSITIVE LOGITS
     นัก
    1.34
    ného
    1.33
    今後
    1.30
    ního
    1.30
     disminuir
    1.29
     merece
    1.28
     methods
    1.27
    ävän
    1.24
    つて
    1.22
     다른
    1.21
    Activations Density 0.016%

    No Known Activations