© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83156
    Prev
    Next
    INDEX
    Explanations

    C/C++ code and function declarations

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

    The neuron fires on tokens that specify or annotate a function’s calling convention or similar linkage attributes (e.g. __cdecl, __stdcall, PROC, THREAD_FUNC_DECL, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     дослі
    -0.84
     chromatin
    -0.77
    作业
    -0.71
    ㄚ
    -0.71
    ложить
    -0.71
    acety
    -0.71
    ashiro
    -0.70
     Typing
    -0.70
     Uniwersyte
    -0.69
     Gables
    -0.68
    POSITIVE LOGITS
     CALL
    1.43
     WIN
    1.24
    CALL
    1.21
    API
    1.18
    DECL
    1.09
     PAS
    1.08
     CD
    1.05
    EXPORT
    1.01
    CD
    1.00
    WIN
    0.98
    Activations Density 0.026%

    No Known Activations