© 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. 34-GEMMASCOPE-RES-131K
    7. 47206
    Prev
    Next
    INDEX
    Explanations

    css box properties

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

    The neuron responds to occurrences of the substring “box” (as in “box‐sizing,” “box‐shadow,” etc.).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Vikipedi
    -0.72
    žová
    -0.68
    جی
    -0.68
    ške
    -0.67
    ३
    -0.67
    穣
    -0.66
    nischen
    -0.66
     Caldwell
    -0.66
     Abd
    -0.66
    sco
    -0.66
    POSITIVE LOGITS
     GMB
    0.68
     Agility
    0.67
     každ
    0.66
    Bernie
    0.65
     瓶
    0.65
    Propri
    0.64
    Agility
    0.64
     POLL
    0.64
     SETTLE
    0.63
     мастер
    0.63
    Activations Density 0.054%

    No Known Activations