© 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. 99568
    Prev
    Next
    INDEX
    Explanations

    geographical regions and bodies of water

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

    This neuron activates on parts of geographic place names, i.e. substrings of proper location 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_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
     anadolu
    -1.58
    )
    -1.55
     comprensión
    -1.48
     テープ
    -1.41
    kita
    -1.35
     méda
    -1.33
     auffi
    -1.33
     lorsque
    -1.32
    lité
    -1.32
     Poultry
    -1.28
    POSITIVE LOGITS
     to
    1.62
     supuestamente
    1.59
    地区的
    1.54
     системой
    1.43
     even
    1.38
     даже
    1.36
     regiones
    1.34
     комна
    1.34
     I
    1.33
    FFFFFF
    1.30
    Activations Density 0.134%

    No Known Activations