© 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. 129457
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on mentions of sliders or carousels (e.g., “слайдер,” “slide,” “carousel”) in code or text.

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

    carousel, slider, swipe, slideshow

    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
    1
    -1.27
    8
    -1.22
    ↵
    -1.22
    2
    -1.13
    就算
    -1.13
    6
    -1.07
    LEVEL
    -1.02
    直接
    -1.02
     /
    -1.02
     is
    -1.02
    POSITIVE LOGITS
     choisissez
    1.31
    紆
    1.23
     {
    1.19
    迫力
    1.16
    1.15
     núcleos
    1.13
    委托
    1.13
    促销
    1.12
    旸
    1.12
    姘
    1.11
    Activations Density 0.017%

    No Known Activations