© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 118744
    Prev
    Next
    INDEX
    Explanations

    css pseudo-elements `:before` and `:after`

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

    CSS pseudo-selectors `:before` and `:after` in code.

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

    The neuron fires on CSS pseudo‐element rules—particularly declarations of “:before” and “:after” (and their accompanying “content” property).

    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
     besucht
    -1.60
    需要
    -1.55
     bekommt
    -1.51
    秾
    -1.50
     abbiamo
    -1.45
    行きたい
    -1.45
     utiliser
    -1.44
    たまに
    -1.42
    衕
    -1.40
    ついに
    -1.38
    POSITIVE LOGITS
     pady
    1.45
    鰍
    1.41
    şey
    1.38
    pä
    1.37
    Produto
    1.37
     dover
    1.37
    uyasha
    1.34
    Algunos
    1.32
    vensko
    1.32
     Gü
    1.30
    Activations Density 0.009%

    No Known Activations