© 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. 22-GEMMASCOPE-RES-131K
    7. 39295
    Prev
    Next
    INDEX
    Explanations

    third round, pole vault, Scottsboro, Plymouth Argyle

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

    This neuron detects two-letter uppercase country or region codes (e.g. “_GH”, “_ZA”, “_AL”) typically used in locale or language–region tags.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     in
    -1.31
    お待ちしております
    -1.24
     by
    -1.14
     on
    -1.06
     Quit
    -1.05
     any
    -1.02
     bigger
    -1.01
     allen
    -1.01
     schwar
    -0.98
     &
    -0.94
    POSITIVE LOGITS
     Posteriormente
    1.34
     exhib
    1.20
     tempera
    1.16
     cortesía
    1.12
     Junto
    1.11
     aandacht
    1.07
     facili
    1.07
     comentários
    1.07
     logistique
    1.04
     vitu
    1.04
    Activations Density 0.069%

    No Known Activations