© 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. 22-GEMMASCOPE-RES-131K
    7. 64413
    Prev
    Next
    INDEX
    Explanations

    css units like px, em, dp

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

    The neuron fires on numeric literals—particularly numbers used in CSS dimension values (e.g. pixel measurements).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    がなく
    -1.53
    ousand
    -1.48
    lxt
    -1.41
     that
    -1.37
     mapas
    -1.34
    acular
    -1.33
     desmotiv
    -1.27
    guigu
    -1.27
    argp
    -1.23
     taką
    -1.23
    POSITIVE LOGITS
    w
    1.61
    p
    1.41
    C
    1.26
    z
    1.25
    b
    1.24
    v
    1.24
    f
    1.20
    form
    1.19
    c
    1.18
    m
    1.18
    Activations Density 0.011%

    No Known Activations