© 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. 48238
    Prev
    Next
    INDEX
    Explanations

    github urls

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

    The neuron activates on occurrences of the “github” domain in URLs.

    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
     in
    -2.63
     for
    -2.44
    ):
    -2.36
        
    -2.36
     która
    -2.28
     has
    -2.23
     if
    -2.23
           
    -2.14
     What
    -2.13
    ........
    -2.11
    POSITIVE LOGITS
    
    2.59
     rése
    2.48
    
    2.42
    镚
    2.39
     花纹
    2.31
     kristal
    2.30
     抠
    2.27
     dezelve
    2.25
     diki
    2.22
     adem
    2.20
    Activations Density 0.014%

    No Known Activations