© 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. 19607
    Prev
    Next
    INDEX
    Explanations

    CSS pseudo-classes or element selectors

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

    The neuron fires on colon characters (":") when they appear in code contexts—e.g. in CSS selectors or jQuery pseudo-classes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    CSS/jQuery selectors that use a leading colon (pseudo-classes and pseudo-elements).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the colon character in CSS pseudo-selectors and pseudo-elements like `:hover`, `:before`, `:after`, `:eq`, `:checked`, `:first-child`, and `:last-child`.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     =
    -2.20
    6
    -2.13
    3
    -2.11
    并且
    -2.00
    //
    -2.00
    f
    -2.00
    two
    -1.95
    after
    -1.95
    4
    -1.95
    and
    -1.94
    POSITIVE LOGITS
    linawan
    1.90
    
    1.77
    కర్య
    1.73
     rápidos
    1.73
    玊
    1.72
    が終わ
    1.71
     nonchal
    1.71
    <bos>
    1.71
     "]";
    1.70
     lentamente
    1.67
    Activations Density 0.006%

    No Known Activations