© 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. 10-GEMMASCOPE-RES-131K
    4. 73047
    Prev
    Next
    INDEX
    Explanations

    scientific paper beginnings

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

    The neuron is keyed to the punctuation that ends author lists in scholarly reference entries—i.e. the period after the authors (e.g. “et al.” or “Smith J.”) in a bibliography.

    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
     them
    -1.53
     coreana
    -1.52
     tekno
    -1.41
     conocidos
    -1.39
     diki
    -1.38
    мая
    -1.35
    久しぶりの
    -1.34
     Hoteles
    -1.34
     dekoratif
    -1.33
     izin
    -1.32
    POSITIVE LOGITS
    </strong>
    1.29
     ‘
    1.18
     Prisoners
    1.18
     rheinland
    1.18
     in
    1.17
     regarding
    1.16
    伙
    1.15
    end
    1.14
     "
    1.11
     =
    1.10
    Activations Density 0.067%

    No Known Activations