© 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. 10-GEMMASCOPE-RES-131K
    7. 87341
    Prev
    Next
    INDEX
    Explanations

    dimensions and line-height

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

    The neuron fires on CSS “line‐height” declarations (i.e. the occurrences of the line‐height property and its numeric values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </h2>
    -2.16
     {
    -1.93
    r
    -1.77
    ↵
    -1.70
     如果
    -1.67
    Then
    -1.59
     proceder
    -1.59
     —
    -1.56
    k
    -1.54
    $
    -1.53
    POSITIVE LOGITS
     innych
    2.14
     سایر
    1.97
    
    1.71
    ஂ
    1.66
     خاصة
    1.66
    再见
    1.63
     інших
    1.63
    瘜
    1.60
     ТЕ
    1.58
    珝
    1.58
    Activations Density 0.001%

    No Known Activations