© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34431
    Prev
    Next
    INDEX
    Explanations

    CSS box and sizing properties

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

    The neuron fires on CSS style values—especially layout and sizing directives like “cover,” “hidden,” “responsive,” and related property 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
    すっ
    -1.18
     parfums
    -1.16
    えっ
    -1.15
     remarkably
    -1.13
     vastly
    -1.09
    いえ
    -1.06
     imprensa
    -1.04
     Japão
    -1.03
     unui
    -1.02
     strikingly
    -1.02
    POSITIVE LOGITS
     people
    1.26
    時間は
    1.22
     time
    1.22
    </h2>
    1.17
     one
    1.14
     tiny
    1.11
     give
    1.11
     while
    1.09
     very
    1.06
     areas
    1.06
    Activations Density 0.001%

    No Known Activations