© 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. 65053
    Prev
    Next
    INDEX
    Explanations

    company names and brands

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

    The neuron fires on corporate or organization names (brand names) mentioned in the 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_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
     as
    -2.20
     ataupun
    -1.70
     umożli
    -1.63
    急忙
    -1.59
     During
    -1.55
     литров
    -1.53
     menjelaskan
    -1.51
     their
    -1.51
     pengetahuan
    -1.51
     avuto
    -1.50
    POSITIVE LOGITS
     necessário
    1.73
    栳
    1.73
     necesario
    1.63
     deft
    1.63
     alguns
    1.59
     které
    1.58
    峮
    1.57
    狨
    1.53
     =
    1.51
    nachweise
    1.48
    Activations Density 0.036%

    No Known Activations