© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60129
    Prev
    Next
    INDEX
    Explanations

    Cook County, Cook Islands

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

    The neuron activates specifically on occurrences of the substring “Cook,” detecting the token “Cook” in proper 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
     catapult
    -2.70
     
    -2.64
    CHREIB
    -2.48
    "
    -2.47
    ～～
    -2.41
     instig
    -2.41
     manoeu
    -2.31
    やはり
    -2.28
    vantaged
    -2.27
     incite
    -2.25
    POSITIVE LOGITS
    {
    3.31
    k
    3.06
     знал
    2.77
     atau
    2.42
     знают
    2.41
    m
    2.41
    »;
    2.39
    鷙
    2.28
     یا
    2.28
     scolas
    2.25
    Activations Density 0.003%

    No Known Activations