© 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. 39141
    Prev
    Next
    INDEX
    Explanations

    URL, Server, screen, child, pyocyanine

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

    The neuron consistently lights up on named-entity–style tokens—proper names, all-caps acronyms, and other entity labels (e.g. company names, gene/protein symbols, or RegExp-style identifiers).

    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
    GRAFÍA
    -1.73
    GRAFIA
    -1.70
    醣
    -1.64
    CCIÓN
    -1.58
    鈣
    -1.38
    けると
    -1.36
    鹼
    -1.34
     boissons
    -1.30
     légumes
    -1.29
    ﹪
    -1.29
    POSITIVE LOGITS
     vinaigre
    1.55
    1.43
    Ἴ
    1.38
    ｪ
    1.38
    いただけ
    1.36
    </h3>
    1.34
     poitrine
    1.34
    くに
    1.33
    くわ
    1.30
     datter
    1.25
    Activations Density 16.023%
    No Known Activations