© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 445
    Prev
    Next
    INDEX
    Explanations

    administrative divisions followed by of

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

    The neuron fires on mentions of administrative subdivisions—terms like province, department, district, canton, region, state, or municipality.

    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
     omdat
    -1.24
     with
    -1.24
     because
    -1.06
     when
    -1.05
     through
    -1.05
     +
    -1.04
     these
    -1.03
    。
    -1.03
     adequately
    -1.02
     will
    -1.02
    POSITIVE LOGITS
     of
    2.17
     informé
    1.24
     monstruo
    1.22
     sosi
    1.20
     laajenta
    1.19
     provincie
    1.19
     sesi
    1.16
     sentier
    1.15
     courants
    1.15
     allemand
    1.15
    Activations Density 0.059%

    No Known Activations