© 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. 34-GEMMASCOPE-RES-131K
    7. 119259
    Prev
    Next
    INDEX
    Explanations

    C++ `::` followed by standard library components

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

    The neuron flags programming‐style text—particularly long runs of punctuation and code syntax like hyphen rulers, angle-bracketed includes, template delimiters, version numbers, and other C++ code tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     eing
    -0.82
    pagna
    -0.76
    osho
    -0.69
     Thrift
    -0.69
    沿い
    -0.69
    harmed
    -0.68
    angat
    -0.67
    紬
    -0.66
     Thank
    -0.66
    虑
    -0.66
    POSITIVE LOGITS
    array
    0.89
    ్య
    0.86
    زی
    0.85
     rowCount
    0.83
    variant
    0.82
    tuple
    0.82
    حوال
    0.82
     ErrorCode
    0.80
     skai
    0.80
     andy
    0.79
    Activations Density 0.083%

    No Known Activations