© 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. 47840
    Prev
    Next
    INDEX
    Explanations

    Cleveland, Gujarat, Ahmedabad

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

    The neuron fires on proper‐name tokens—especially sports teams, cities, and individual person 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
    \
    -1.39
    &
    -1.28
     has
    -1.25
    +
    -1.23
    er
    -1.20
    -
    -1.20
     завдання
    -1.17
    _
    -1.17
    现在
    -1.16
    3
    -1.16
    POSITIVE LOGITS
     saar
    1.41
    捋
    1.33
     tait
    1.30
    itars
    1.29
     Ahmedabad
    1.29
     Gujarati
    1.28
    PAG
    1.28
     thermomix
    1.27
     geda
    1.27
     uhr
    1.25
    Activations Density 0.135%

    No Known Activations