© 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. 34-GEMMASCOPE-RES-131K
    7. 77177
    Prev
    Next
    INDEX
    Explanations

    inline-block css declarations

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

    The neuron fires on CSS “display” declarations—especially the keyword “inline” (as in “display: inline” or “inline-block”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    基
    -0.82
     adolescentes
    -0.74
    *]
    -0.71
     turtles
    -0.71
    isseur
    -0.70
    Zn
    -0.70
     Luffy
    -0.67
     súng
    -0.67
     wenden
    -0.67
     Options
    -0.66
    POSITIVE LOGITS
     BLOCK
    1.04
    blocking
    0.99
    block
    0.99
     block
    0.98
     blocking
    0.97
    Block
    0.90
    Blocking
    0.84
     Blocking
    0.81
    ったのは
    0.79
    BLOCK
    0.78
    Activations Density 0.030%

    No Known Activations