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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 131021
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to layout‐direction settings—e.g. XML orientation attributes or CSS flex-direction declarations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    layout orientation and flex

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     to
    -1.30
     by
    -1.13
     attacc
    -0.98
     from
    -0.98
    Cater
    -0.93
     окно
    -0.88
    Expan
    -0.86
    .
    -0.86
    olah
    -0.86
     and
    -0.85
    POSITIVE LOGITS
    kowej
    1.31
     aldea
    1.20
    ()`
    1.16
     구성
    1.12
     tidigare
    1.10
     frequentemente
    1.10
     följande
    1.08
     pourrait
    1.08
    布局
    1.06
     composto
    1.05
    Activations Density 0.015%

    No Known Activations