© 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. 104542
    Prev
    Next
    INDEX
    Explanations

    Borg and cyborg

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

    This neuron detects occurrences of the substring “borg,” whether as the standalone name “Borg” or embedded in words like “cyborg.”

    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
    🩻
    -3.06
    lossians
    -3.03
    🫃
    -3.02
    骉
    -2.81
    铊
    -2.78
    咈
    -2.70
    拮
    -2.66
    dientemente
    -2.56
    绀
    -2.55
    縋
    -2.55
    POSITIVE LOGITS
    {
    3.56
    —
    3.06
    &
    2.91
    to
    2.83
    X
    2.78
    z
    2.64
    k
    2.64
     Некоторые
    2.55
    D
    2.50
    id
    2.48
    Activations Density 0.004%

    No Known Activations