© 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. 72904
    Prev
    Next
    INDEX
    Explanations

    interface/对话框/跳转

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

    The neuron activates on tokens that look like code‐style identifiers or paths—i.e. tokens containing punctuation such as dots or slashes (URLs, file paths, module or interface 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
      
    -2.91
     
    -2.86
     “
    -2.69
    ↵
    -2.63
     Hinblick
    -2.42
    起了
    -2.33
        
    -2.27
    o
    -2.27
    {
    -2.25
    e
    -2.20
    POSITIVE LOGITS
    s
    2.84
    tedì
    2.72
    ⎚
    2.63
    ⢌
    2.58
    訁
    2.58
    ﮩ
    2.53
    ዡ
    2.53
    涠
    2.48
    sekten
    2.48
     articolo
    2.48
    Activations Density 0.001%

    No Known Activations