© 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. 101765
    Prev
    Next
    INDEX
    Explanations

    web page views

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

    the word "view" in programming code contexts, particularly in web development frameworks.

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

    This neuron detects references to view‐template files or includes (e.g. “view”, JSP include/page directives, file paths to views).

    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
    ),
    -1.84
    //
    -1.69
    v
    -1.65
    g
    -1.63
    t
    -1.63
    n
    -1.59
    the
    -1.58
     =
    -1.56
     также
    -1.55
    m
    -1.51
    POSITIVE LOGITS
     gouden
    1.78
     volledige
    1.78
     materialen
    1.75
     verschillen
    1.71
     oplossing
    1.70
     onderhoud
    1.68
     geluid
    1.66
     unieke
    1.61
     mijne
    1.60
     geschenk
    1.59
    Activations Density 0.017%

    No Known Activations