© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128500
    Prev
    Next
    INDEX
    Explanations

    This neuron detects country names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    countries, cities, and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     both
    -1.40
     on
    -1.31
     only
    -1.27
     that
    -1.22
     as
    -1.19
     then
    -1.18
     first
    -1.14
     their
    -1.14
     out
    -1.12
     really
    -1.10
    POSITIVE LOGITS
    
    1.23
    several
    1.19
    BEFORE
    1.16
     alcuni
    1.16
     plusieurs
    1.15
     tenemos
    1.13
    锨
    1.13
     некоторых
    1.12
    despite
    1.12
     privata
    1.09
    Activations Density 0.051%

    No Known Activations