© 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. 102212
    Prev
    Next
    INDEX
    Explanations

    regions and directions

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

    The neuron fires strongly on names of geographic regions and place names (e.g. states, coasts, regions).

    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
     when
    -1.30
     når
    -1.26
    culously
    -1.20
    Ingredi
    -1.13
    Noter
    -1.12
     a
    -1.10
     activism
    -1.09
    []
    -1.09
     coda
    -1.08
    encji
    -1.08
    POSITIVE LOGITS
     of
    1.45
    特别是
    1.27
     parts
    1.22
    付近
    1.13
     I
    1.13
    ॲ
    1.13
    ⼤
    1.11
    criminate
    1.10
     erste
    1.09
    m
    1.09
    Activations Density 0.046%

    No Known Activations