© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66315
    Prev
    Next
    INDEX
    Explanations

    Academic proceedings and symposia

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

    The neuron detects bibliographic reference markers—especially numeric volume, page, year, and conference abbreviations in citations.

    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
    льевич
    -0.84
    ඨ
    -0.79
    ம்
    -0.77
     时间
    -0.76
    もん
    -0.76
     once
    -0.76
    Shortly
    -0.75
    📻
    -0.75
    ufort
    -0.75
    Once
    -0.75
    POSITIVE LOGITS
     Proceedings
    1.13
     NATO
    1.10
     proceedings
    1.10
     symposium
    1.10
     SCOPE
    1.02
    Proceedings
    1.02
     attendees
    0.95
    volume
    0.94
     Symposium
    0.93
     szer
    0.93
    Activations Density 0.013%

    No Known Activations