© 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. 86653
    Prev
    Next
    INDEX
    Explanations

    clang support

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

    The neuron activates on occurrences of the substring “clang” (e.g. tool names like clang, clang-format, 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_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
     маленьких
    -2.63
    菝
    -2.59
    
    -2.47
    谖
    -2.44
    脔
    -2.44
    atrician
    -2.41
     camiset
    -2.41
    
    -2.39
    瞜
    -2.38
     всѣ
    -2.36
    POSITIVE LOGITS
    {
    3.03
    ’
    2.91
     and
    2.27
    1
    2.27
     clang
    2.22
    2
    2.13
    ↵↵
    2.09
    in
    2.05
     fortu
    2.05
     gratuita
    2.02
    Activations Density 0.010%

    No Known Activations