© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71633
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

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

    The neuron fires on programming API or library method calls—i.e. camel-cased function or service invocation names in code.

    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
    </strong>
    -2.63
    </h3>
    -2.61
    </em>
    -2.33
    ໊
    -2.17
     COMPOUNDS
    -2.06
     hochwer
    -2.05
    新た
    -2.02
    ↵
    -2.00
    <em>
    -1.99
     limitless
    -1.95
    POSITIVE LOGITS
    骉
    2.73
     durante
    2.48
     alcuni
    2.34
    
    2.34
     alcune
    2.31
     They
    2.28
    噥
    2.25
     diversos
    2.20
    The
    2.19
     英語
    2.14
    Activations Density 0.000%

    No Known Activations