© 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. 86935
    Prev
    Next
    INDEX
    Explanations

    initialization calls like init()

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

    The neuron fires on the “&” address‐of operator token (especially when used as a function argument).

    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
     siè
    -1.81
    訁
    -1.73
     Dinas
    -1.72
    沵
    -1.72
    
    -1.70
    튿
    -1.70
    
    -1.66
     negru
    -1.63
     trés
    -1.63
    taient
    -1.63
    POSITIVE LOGITS
     in
    2.42
     by
    2.34
     on
    2.22
     an
    2.20
     for
    2.17
     at
    2.14
     it
    2.13
     the
    1.95
     this
    1.92
     There
    1.92
    Activations Density 0.002%

    No Known Activations