© 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. 22-GEMMASCOPE-RES-131K
    4. 74925
    Prev
    Next
    INDEX
    Explanations

    institution and affiliation names

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

    The neuron fires on multiword, capitalized organization or institution names (e.g. universities, colleges, research institutes, professional bodies).

    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
     to
    -1.55
     творо
    -1.27
    家は
    -1.23
    再度
    -1.17
    7
    -1.12
    8
    -1.11
     نمایید
    -1.09
     gamme
    -1.07
     naturen
    -1.05
    这让
    -1.04
    POSITIVE LOGITS
     elég
    1.28
     obuv
    1.14
     The
    1.11
     But
    1.10
    СТА
    1.09
     termé
    1.09
     stratég
    1.09
     Below
    1.06
     So
    1.06
     Even
    1.02
    Activations Density 0.061%

    No Known Activations