© 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. 101817
    Prev
    Next
    INDEX
    Explanations

    Software, OS, and organizations

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

    proper nouns related to technology brands and products, particularly software, operating systems, and car manufacturers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on capitalized technology and platform names (e.g. operating systems, Linux distributions, cloud providers, and other vendor or product 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
     ongles
    -1.72
     solides
    -1.67
     êtres
    -1.60
     énorm
    -1.59
     éto
    -1.52
     potenci
    -1.51
    幼儿
    -1.46
     dépla
    -1.46
     lesquelles
    -1.45
     éner
    -1.45
    POSITIVE LOGITS
     to
    2.09
    ↵↵
    2.00
     and
    1.95
     is
    1.88
     will
    1.59
     of
    1.54
    lognese
    1.48
     has
    1.38
    ATIVA
    1.34
    뿔
    1.33
    Activations Density 8.749%

    No Known Activations