© 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. 22-GEMMASCOPE-RES-131K
    7. 40286
    Prev
    Next
    INDEX
    Explanations

    C++ code with assertions

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

    The neuron fires on uppercase code tokens—especially macros, constants, and other all‐caps identifiers in programming 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_22/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
    '
    -1.27
     wodurch
    -1.19
    ;
    -1.18
     th
    -1.16
     fifteen
    -1.09
    也可
    -1.09
     From
    -1.08
     an
    -1.08
    N
    -1.07
     sixteen
    -1.06
    POSITIVE LOGITS
     gelatina
    1.50
    1.45
     camiset
    1.38
    brainly
    1.38
     asfalto
    1.37
     patata
    1.37
    訫
    1.36
     monstruos
    1.36
    <bos>
    1.34
    1.34
    Activations Density 0.008%

    No Known Activations