© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33007
    Prev
    Next
    INDEX
    Explanations

    CSS properties

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

    The neuron fires on numeric literal tokens in code (e.g. pixel values, hex digits, or other numbers in CSS/HTML).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     plafon
    -2.17
     romantis
    -1.96
     kalender
    -1.94
     atlet
    -1.88
     türkiye
    -1.85
     menik
    -1.84
     kompati
    -1.80
     pittores
    -1.80
     célè
    -1.80
     galeri
    -1.78
    POSITIVE LOGITS
    Y
    1.92
    _
    1.91
     J
    1.89
     L
    1.84
     W
    1.81
     M
    1.81
     has
    1.80
    ’
    1.77
     O
    1.74
    L
    1.73
    Activations Density 0.009%

    No Known Activations