© 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. 97923
    Prev
    Next
    INDEX
    Explanations

    programming structure annotations

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

    The neuron is picking up PHPDoc “@var” type‐annotation lines (i.e. type declarations in docblock comments).

    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
    而不是
    -0.93
    Ār
    -0.92
     手工
    -0.92
    んですね
    -0.91
     educação
    -0.88
    Covid
    -0.87
     jednego
    -0.85
    Partici
    -0.85
     教室
    -0.85
    릭
    -0.85
    POSITIVE LOGITS
     mixed
    1.85
    string
    1.83
    mixed
    1.82
     string
    1.71
     array
    1.64
     int
    1.49
     bool
    1.43
    int
    1.41
    array
    1.34
     null
    1.33
    Activations Density 0.013%

    No Known Activations