© 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. 71489
    Prev
    Next
    INDEX
    Explanations

    css height definitions

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

    The neuron selectively activates on CSS length values specified in pixels (e.g. “40px”).

    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
    -1.20
     INFORMACIÓN
    -1.09
    ävän
    -1.06
     Commencez
    -1.05
    dois
    -1.05
     Krieges
    -1.03
    それぞれ
    -1.03
    these
    -1.02
     徒歩
    -0.99
     Partagez
    -0.97
    POSITIVE LOGITS
    IQUE
    1.10
     évidemment
    1.04
     and
    1.03
    看了一眼
    0.98
    tieron
    0.97
     oferece
    0.97
     fué
    0.96
    ٥
    0.94
     lançado
    0.94
    dog
    0.94
    Activations Density 0.005%

    No Known Activations