© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103570
    Prev
    Next
    INDEX
    Explanations

    layout positioning and spacing

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

    The neuron fires on numeric literals in code (e.g. dimension or coordinate values such as layout margins, padding, widths, etc.).

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

    No Comments

    Negative Logits
     that
    -1.84
     become
    -1.68
    ↵↵↵
    -1.51
    ?
    -1.50
     there
    -1.50
     evidently
    -1.49
     if
    -1.48
     numerous
    -1.47
     while
    -1.45
     undoubtedly
    -1.43
    POSITIVE LOGITS
    髣
    1.82
    Elaboración
    1.71
     --->
    1.68
    姩
    1.62
    Ruju
    1.59
     Dinas
    1.55
    
    1.55
    骤
    1.53
    尨
    1.52
     着物
    1.51
    Activations Density 0.016%

    No Known Activations