© 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. 102640
    Prev
    Next
    INDEX
    Explanations

    C/C++ string manipulation

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

    C/C++ `#include <string>` or `#include <string.h>` directives in source code.

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

    The neuron specifically fires on occurrences of the C++ `<string>` header in include directives.

    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
    r
    -1.73
     behaves
    -1.63
     จาก
    -1.63
    裢
    -1.59
    ——————
    -1.59
     spearheaded
    -1.59
     our
    -1.57
     progresso
    -1.56
    我们就
    -1.55
    禇
    -1.55
    POSITIVE LOGITS
    ↵↵
    1.84
    その
    1.53
    巔
    1.50
    quisition
    1.49
    ).
    1.48
     varför
    1.46
    crimination
    1.43
    1.43
    )$
    1.38
    '}}>
    1.36
    Activations Density 0.006%

    No Known Activations