© 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. 22-GEMMASCOPE-RES-131K
    7. 39428
    Prev
    Next
    INDEX
    Explanations

    razor page code

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

    The neuron fires on occurrences of the programming‐related token “Page” or “Pages” (e.g. in Razor/ASP.NET code identifiers and namespaces).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     förslag
    -1.10
    0
    -1.09
    5
    -1.06
     的
    -1.05
    ?
    -1.01
     tästä
    -0.99
    ارس
    -0.99
    II
    -0.98
     spelar
    -0.98
     ytterligare
    -0.97
    POSITIVE LOGITS
    ,  
    1.17
     bì
    1.16
    的情况下
    1.16
    ¹,
    1.14
    比较好
    1.13
    ⽅
    1.13
     \&
    1.10
    віти
    1.09
    ladora
    1.09
     
    1.08
    Activations Density 0.002%

    No Known Activations