© 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. 22-GEMMASCOPE-RES-131K
    7. 104727
    Prev
    Next
    INDEX
    Explanations

    PLOS ONE journal articles or technical forums

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

    The neuron strongly activates on bibliographic/citation metadata—things like journal names, article identifiers, DOIs, and URL or section codes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ThroughAttribute
    -1.02
    日曜日
    -1.02
    !/
    -1.00
     papillon
    -0.98
     поиск
    -0.93
    Ύ
    -0.92
    “:
    -0.91
    parseDouble
    -0.91
    ()],
    -0.90
     frites
    -0.90
    POSITIVE LOGITS
    govine
    0.96
    佘
    0.95
     visión
    0.95
     tikai
    0.94
    Eerste
    0.93
    SOME
    0.93
     ısı
    0.91
    hirkan
    0.91
     loro
    0.90
    Mijn
    0.90
    Activations Density 0.000%

    No Known Activations