© 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. 66531
    Prev
    Next
    INDEX
    Explanations

    international affiliations and locations

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

    The neuron detects institutional affiliation lines in academic papers, especially the place names (cities, countries) and numbered superscripts marking authors’ institutions.

    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
     конец
    -1.18
     целью
    -1.13
     it
    -1.12
     цель
    -1.07
     całą
    -1.05
     column
    -1.05
     deportivas
    -1.02
     końca
    -1.02
     users
    -1.00
    moine
    -1.00
    POSITIVE LOGITS
    zzling
    1.17
    ypso
    1.13
    нє
    1.12
    pergillus
    1.12
     triomphe
    1.11
    𝕿
    1.11
    ји
    1.10
     ندار
    1.09
    日本の
    1.06
    Energie
    1.05
    Activations Density 0.001%

    No Known Activations