© 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. 33674
    Prev
    Next
    INDEX
    Explanations

    rounded corners and radius

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

    The neuron detects mentions of geometric rounding (e.g. “round,” “rounded,” “rounding,” “border-radius,” and the SVG “r” attribute).

    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
    ',
    -1.22
     łyż
    -1.22
     должен
    -1.11
     ocorrer
    -1.10
    исправ
    -1.09
     бел
    -1.09
     занимает
    -1.08
    -1.08
     fondamentali
    -1.07
    ное
    -1.06
    POSITIVE LOGITS
    Antal
    1.13
    Mitar
    1.13
    Trout
    1.12
    Tó
    1.08
    izamos
    1.06
    ニーズ
    1.05
    Tapi
    1.05
     creating
    1.04
     نرم
    1.03
     inicios
    1.03
    Activations Density 0.007%
    No Known Activations