© 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. 119575
    Prev
    Next
    INDEX
    Explanations

    Nexenta, Nexstar, Nextel, Nexbox

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

    This neuron responds to tokens containing the letter sequence “nex” (as in Nextera, NEXIS, NexTel, etc.).

    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
    有名な
    -2.52
    玏
    -2.50
    '));
    -2.48
    ⦊
    -2.47
    ?”
    -2.45
    
    -2.41
    
    -2.34
    ꦁ
    -2.31
    Ꮀ
    -2.31
     verschill
    -2.22
    POSITIVE LOGITS
    s
    3.94
    公司的
    2.64
     They
    2.56
    ↵↵
    2.50
    they
    2.44
     I
    2.44
    )
    2.44
    也是
    2.36
    但在
    2.33
     ….
    2.27
    Activations Density 0.043%

    No Known Activations