© 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. 100087
    Prev
    Next
    INDEX
    Explanations

    declaration syntax

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

    the keyword "const" in programming code, particularly in C/C++ variable and parameter declarations.

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

    This neuron activates on C/C++ type qualifiers and storage-class specifiers (e.g., const, volatile, inline, and related keywords).

    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
    ’
    -1.48
     techniczne
    -1.32
     sanoo
    -1.32
    ̀nh
    -1.28
     relies
    -1.28
     autorizado
    -1.27
     tehdä
    -1.27
    復興
    -1.26
    Setiap
    -1.26
     any
    -1.26
    POSITIVE LOGITS
     Namun
    1.55
    ᯾
    1.50
     trám
    1.37
    gning
    1.37
    ähn
    1.34
    fél
    1.33
     Новости
    1.33
    pozorn
    1.30
    ributes
    1.29
    
    1.29
    Activations Density 0.004%

    No Known Activations