© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67138
    Prev
    Next
    INDEX
    Explanations

    Columbus and its associated places

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

    The neuron fires in response to occurrences of the proper noun “Columbus.”

    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
    ’
    -2.34
    蔔
    -2.30
    A
    -2.22
     допо
    -2.13
     if
    -2.08
    E
    -2.06
     удалить
    -2.05
     стаття
    -2.03
    良い
    -2.03
    比起
    -2.02
    POSITIVE LOGITS
     He
    2.30
     criou
    2.22
    鼱
    2.19
    纛
    2.17
     decidiu
    2.17
    
    2.17
    
    2.16
    bacteria
    2.16
     付き
    2.14
    一定会
    2.11
    Activations Density 0.003%

    No Known Activations