© 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. 118796
    Prev
    Next
    INDEX
    Explanations

    web browser components

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

    references to web browsers, especially Safari and WebView components in technical or programming contexts.

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

    The neuron fires on mentions of web browser names and related browser/inspector tools (e.g. “Safari,” “Web,” “Browser,” “Inspector,” “Element”).

    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
    ти
    -1.34
    another
    -1.29
     derniers
    -1.27
     kunst
    -1.26
    '}';
    -1.23
    typical
    -1.23
     elektrik
    -1.19
     Audiodateien
    -1.17
     '/',
    -1.16
     Eſ
    -1.16
    POSITIVE LOGITS
     both
    1.41
    ers
    1.33
     on
    1.32
     homenagem
    1.31
     maupun
    1.31
    نش
    1.25
     beträ
    1.20
     sizable
    1.18
     keinerlei
    1.17
     What
    1.16
    Activations Density 0.085%

    No Known Activations