© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8258
    Prev
    Next
    INDEX
    Explanations

    grid, G, GPT

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

    tokens related to CSS layout properties and values (especially CSS Grid properties like grid, grid-template-columns, gap, margin, width).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ut
    0.85
    ab
    0.72
    un
    0.66
    d
    0.59
    го
    0.58
    ren
    0.57
    can
    0.57
    ang
    0.57
    ul
    0.52
    az
    0.52
    POSITIVE LOGITS
    ன்
    0.69
    า
    0.69
     писа
    0.67
    ु
    0.65
    ל
    0.64
    л
    0.62
    ਰ
    0.61
     reshaping
    0.61
    يد
    0.59
    لى
    0.59
    Activations Density 0.503%

    No Known Activations