© 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. 22-GEMMASCOPE-RES-131K
    7. 26283
    Prev
    Next
    INDEX
    Explanations

    make( or Object(

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

    The neuron fires on occurrences of the identifier “make” when used as a function or macro name 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_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
    ！(
    -1.42
    鹩
    -1.41
    ～！
    -1.40
    Ꮫ
    -1.39
    ～。
    -1.37
    lamps
    -1.29
    〜。
    -1.27
    はなく
    -1.27
    はありません
    -1.24
    тации
    -1.24
    POSITIVE LOGITS
    செ
    1.27
     frecuentemente
    1.22
    西亚
    1.20
    ichteten
    1.17
     supuestamente
    1.17
     vardı
    1.16
    He
    1.16
     мужская
    1.16
    </h4>
    1.14
     olyan
    1.13
    Activations Density 0.001%

    No Known Activations