© 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. 120148
    Prev
    Next
    INDEX
    Explanations

    embedded software, memory, systems

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

    the word "embedded" in technical contexts related to computer systems, memory, or software.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The main thing this neuron does is detect occurrences of the word “embedded.”

    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
     he
    -2.89
    瓩
    -2.86
     avec
    -2.86
     {
    -2.48
     も
    -2.48
     ใช้
    -2.44
    enablog
    -2.42
    屛
    -2.42
    ㋛
    -2.34
    籥
    -2.34
    POSITIVE LOGITS
    ୌ
    3.17
    jaqueta
    3.06
    ଃ
    2.92
    趼
    2.83
    欵
    2.73
    賔
    2.72
     kleines
    2.70
    ௅
    2.66
    灕
    2.64
    नलोड
    2.63
    Activations Density 0.005%

    No Known Activations