© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28489
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes

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

    The neuron detects numeric literals (integer or decimal values) in code (e.g. CSS properties, style attributes, data attributes).

    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
     to
    -1.97
     it
    -1.11
     Talvez
    -1.09
     such
    -1.00
    に行って
    -0.96
    castic
    -0.94
    ogyn
    -0.94
    ㈱
    -0.93
    に行った
    -0.93
    ナメント
    -0.93
    POSITIVE LOGITS
     églises
    1.17
     לך
    1.11
     לכם
    1.10
     vinos
    1.03
     můžete
    1.00
    今回は
    1.00
     effectually
    0.99
     élégant
    0.99
     Fractions
    0.99
    これは
    0.98
    Activations Density 0.001%

    No Known Activations