© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91883
    Prev
    Next
    INDEX
    Explanations

    web page

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

    The neuron fires strongly on programming-language import/include statements (e.g. require, from, include) in code.

    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
     exclusivas
    -0.85
     geldi
    -0.84
    ኘ
    -0.80
    راضي
    -0.80
    GIO
    -0.79
     kolye
    -0.79
     zij
    -0.79
     Arbor
    -0.78
    Türkiye
    -0.78
    tový
    -0.78
    POSITIVE LOGITS
     page
    1.08
    openqa
    1.04
    page
    0.98
     pages
    0.93
    Page
    0.93
     PAGE
    0.89
     Page
    0.88
    PAGE
    0.80
     페이지
    0.79
    niejszych
    0.75
    Activations Density 0.001%

    No Known Activations