© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 26896
    Prev
    Next
    INDEX
    Explanations

    color CSS property

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

    This neuron detects CSS color literals (hex or rgba values) in style declarations.

    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
     These
    -1.38
     but
    -1.37
     What
    -1.34
     However
    -1.34
     would
    -1.28
     This
    -1.20
     as
    -1.18
    が高い
    -1.15
     где
    -1.15
     Ganzen
    -1.14
    POSITIVE LOGITS
     atak
    1.41
     tornillos
    1.41
     aktiviteter
    1.33
     nowy
    1.31
     botones
    1.27
     hermosos
    1.27
     первом
    1.25
     великолеп
    1.25
     fut
    1.23
     colgantes
    1.23
    Activations Density 0.002%

    No Known Activations