© 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. 93379
    Prev
    Next
    INDEX
    Explanations

    scientific institutions and affiliations

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

    research institutions and national laboratories in scientific papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is tuned to detect numeric tokens and digit sequences (e.g. years, footnote indices, affiliation superscripts) in academic text.

    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
     your
    -1.30
     seguente
    -1.27
     Maybe
    -1.27
    Maybe
    -1.25
     &
    -1.20
     Verkaufs
    -1.17
    While
    -1.16
    感じが
    -1.13
     getSource
    -1.12
     alertDialog
    -1.12
    POSITIVE LOGITS
     SUCH
    1.48
    起来的
    1.20
    forschung
    1.18
     research
    1.17
     chercheurs
    1.16
     researchers
    1.16
     TRAD
    1.13
     spezi
    1.12
     scientists
    1.09
     ciutat
    1.09
    Activations Density 0.057%

    No Known Activations