© 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. 95503
    Prev
    Next
    INDEX
    Explanations

    Basque Country and Spain

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

    This neuron fires on geographic location names (city or region 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_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
    出一
    -1.16
     "
    -1.11
    ly
    -1.09
     forne
    -1.05
    كونات
    -1.04
     bereits
    -1.03
    Deportes
    -1.03
     for
    -1.03
     спать
    -1.02
     Canadian
    -1.01
    POSITIVE LOGITS
     it
    1.36
     samti
    1.34
    ഃ
    1.30
    ٙ
    1.22
     deseado
    1.22
     calore
    1.21
     parecido
    1.20
     vinculado
    1.20
    还不错
    1.19
     usata
    1.18
    Activations Density 0.004%

    No Known Activations