© 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. 10839
    Prev
    Next
    INDEX
    Explanations

    CSS prefixes: moz, ms

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

    The neuron detects CSS properties that include vendor-specific prefixes (e.g. “-webkit-…”, “-moz-…”, “-ms-…”).

    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
     beendet
    -1.07
     económico
    -1.05
     aseg
    -1.04
     “
    -1.02
     mises
    -1.02
     גם
    -1.01
     his
    -1.01
    ſelf
    -1.00
     reichen
    -0.96
     très
    -0.94
    POSITIVE LOGITS
    عنی
    1.14
    Kindle
    1.08
     petto
    1.06
     Lond
    1.05
     marito
    1.04
    ֺ
    1.02
     Redewendung
    1.02
    現状
    1.01
    CIUDAD
    1.00
    точници
    0.99
    Activations Density 0.004%

    No Known Activations