© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68512
    Prev
    Next
    INDEX
    Explanations

    background properties

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

    The neuron fires on CSS “background” lines—especially when specifying colors or gradients (e.g. background-color or background-image/linear-gradient).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     WERE
    -1.73
    ER
    -1.68
    -1.67
    </td>
    -1.53
    但他
    -1.52
    </sup>
    -1.48
     WHEN
    -1.48
    翃
    -1.48
    至于
    -1.45
    igth
    -1.45
    POSITIVE LOGITS
    USTOM
    1.73
    kunjung
    1.43
    Owl
    1.41
    𓆜
    1.39
    pieza
    1.33
     می‌توانید
    1.31
    𖣘
    1.31
    công
    1.28
    闰
    1.28
    噚
    1.27
    Activations Density 0.023%

    No Known Activations