© 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. 10-GEMMASCOPE-RES-131K
    4. 10294
    Prev
    Next
    INDEX
    Explanations

    copyright headers and C++ destructors

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

    the tilde symbol (~) used as a destructor operator in C++ code.

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

    This neuron detects the tilde character “~,” most prominently in C++ destructor declarations.

    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
    楽しめます
    -1.61
     reducir
    -1.51
     Why
    -1.48
     We
    -1.45
     宣传
    -1.42
     Cuando
    -1.42
     nossos
    -1.42
    
    -1.41
     What
    -1.39
    >}
    -1.39
    POSITIVE LOGITS
     hırka
    1.91
     muñeco
    1.88
    橚
    1.84
     kaplama
    1.66
    کیف
    1.66
     ahşap
    1.65
     Catedral
    1.61
     پایان
    1.61
     of
    1.60
     eşofman
    1.59
    Activations Density 0.001%

    No Known Activations