© 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. 98514
    Prev
    Next
    INDEX
    Explanations

    World Economic Forum contexts

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

    The neuron fires on high‐profile, headline-style or title words (particularly capitalized proper nouns and section headings) in news or document headings.

    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
     NPD
    -0.72
     trompe
    -0.72
    لح
    -0.72
     التد
    -0.70
     wohin
    -0.69
     reafon
    -0.69
    ühren
    -0.69
     phóng
    -0.69
    MSI
    -0.67
    GetMapping
    -0.66
    POSITIVE LOGITS
     Davos
    2.38
     WE
    2.05
     Schwab
    1.71
    WE
    1.59
    Dav
    1.58
     Klaus
    1.57
    Klaus
    1.38
     DAV
    1.35
    Schw
    1.28
     World
    1.26
    Activations Density 0.014%

    No Known Activations