© 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. 27334
    Prev
    Next
    INDEX
    Explanations

    background color and CSS attributes

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

    This neuron detects “background” or “bgcolor” style attribute tokens (i.e. background‐color settings) in code.

    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
     světa
    -1.52
    矗
    -1.48
     osal
    -1.43
    zembro
    -1.40
     včetně
    -1.38
    äsche
    -1.36
    ӵ
    -1.35
    ůli
    -1.34
    ,’
    -1.32
    在哪里
    -1.31
    POSITIVE LOGITS
    ↵
    1.56
    .
    1.47
     trouvé
    1.46
    dersfield
    1.41
     alguns
    1.18
    UNITIES
    1.17
    ztes
    1.13
     essayé
    1.13
     justru
    1.13
    講師
    1.13
    Activations Density 0.000%

    No Known Activations