© 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. 10-GEMMASCOPE-RES-131K
    7. 118840
    Prev
    Next
    INDEX
    Explanations

    utility and move in C++

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

    C++ standard library header includes, particularly `<memory>` and `<utility>`.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects C/C++ “#include <…>” lines, especially standard‐library headers in angle brackets.

    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
     Bereichen
    -1.39
     ähnliche
    -1.38
     “
    -1.30
     bedeutend
    -1.30
     différentes
    -1.30
     Geschä
    -1.29
     sicherzustellen
    -1.29
     renowned
    -1.27
     bekannten
    -1.24
     geringe
    -1.24
    POSITIVE LOGITS
     more
    1.68
    There
    1.54
    Another
    1.44
    Shortly
    1.34
    When
    1.33
    They
    1.31
     vivido
    1.30
     oddly
    1.26
     strangely
    1.26
     less
    1.26
    Activations Density 0.036%

    No Known Activations