© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38688
    Prev
    Next
    INDEX
    Explanations

    css colors and backgrounds

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

    This neuron detects CSS color declarations (e.g. “color:” or “background[-]color:” with their color values).

    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
     it
    -1.29
    ꯠ
    -1.19
     its
    -1.16
    üyada
    -1.12
     FANDOM
    -1.10
    Эти
    -1.10
    だからこそ
    -1.05
    phäre
    -1.03
    chtenstein
    -1.01
    pagnole
    -1.01
    POSITIVE LOGITS
    jaket
    1.21
    izzling
    1.13
    vernote
    1.10
     військо
    1.09
    nissan
    1.05
    origami
    1.04
    sandal
    1.03
    casque
    1.02
    ducati
    1.02
    mickey
    1.02
    Activations Density 0.003%

    No Known Activations