© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43445
    Prev
    Next
    INDEX
    Explanations

    fixed positioning

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

    The neuron strongly activates on CSS selectors (especially class selectors and other rule names) in style blocks.

    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
     of
    -1.59
    Warna
    -1.57
     dekoratif
    -1.48
    苼
    -1.47
    Catatan
    -1.46
     موب
    -1.42
     την
    -1.41
    睃
    -1.41
    EXERC
    -1.41
    WITHOUT
    -1.39
    POSITIVE LOGITS
     always
    1.63
    та
    1.53
     can
    1.52
     sometimes
    1.52
     continue
    1.51
     establish
    1.51
     may
    1.46
     become
    1.45
     begins
    1.45
     gets
    1.44
    Activations Density 0.002%

    No Known Activations