© 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. 1672
    Prev
    Next
    INDEX
    Explanations

    people groups and affiliations

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

    The neuron detects capitalized organization and event names (especially multi‐word titles or acronyms).

    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
     üblichen
    -1.39
     übrigen
    -1.38
    出来ました
    -1.38
     täglichen
    -1.36
     troubled
    -1.34
     desemple
    -1.32
     magasiner
    -1.30
     beantragt
    -1.29
     acoged
    -1.27
     faltar
    -1.26
    POSITIVE LOGITS
    ViewChild
    1.34
    !
    1.32
     noong
    1.30
     and
    1.28
    љу
    1.27
    DRC
    1.25
    ⅼ
    1.22
     &
    1.20
     then
    1.16
    OURCES
    1.16
    Activations Density 0.045%

    No Known Activations