© 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. 9660
    Prev
    Next
    INDEX
    Explanations

    companies and products

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

    The neuron activates on capitalized proper nouns—especially technology/product names, software titles, and brand or company names.

    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
    rát
    -1.28
    vábbi
    -1.24
     itself
    -1.18
    ностях
    -1.16
     celle
    -1.15
    ξης
    -1.13
     referirse
    -1.12
     aspek
    -1.11
     juguete
    -1.11
    ziehung
    -1.11
    POSITIVE LOGITS
     who
    1.42
     should
    1.28
     by
    1.21
    ,
    1.21
     but
    1.20
     than
    1.15
     to
    1.14
    comuna
    1.05
    Mediabestanden
    1.04
     execu
    1.01
    Activations Density 0.251%

    No Known Activations