© 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. 10-GEMMASCOPE-RES-131K
    7. 28990
    Prev
    Next
    INDEX
    Explanations

    printing and publishing context

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

    The neuron fires on publisher names, imprint statements, and other bibliographic‐citation elements (e.g. “Oxford University Press,” “Polity Books,” volume/page numbers).

    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
     bricola
    -1.82
     boute
    -1.73
    隳
    -1.66
    namely
    -1.66
    
    -1.64
     leopardo
    -1.63
     ananas
    -1.63
     lampe
    -1.58
     paillettes
    -1.58
     abbildung
    -1.55
    POSITIVE LOGITS
     after
    2.09
     during
    1.79
     शुर
    1.73
     before
    1.66
     после
    1.65
     for
    1.58
     started
    1.55
     began
    1.52
     gave
    1.48
     first
    1.48
    Activations Density 0.007%

    No Known Activations