© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9245
    Prev
    Next
    INDEX
    Explanations

    padding and spacing

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

    This neuron detects layout/formatting terms related to spacing (e.g., margin, padding, gap).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    world
    0.58
    খা
    0.55
    ويس
    0.54
    সুতরাং
    0.54
    滃
    0.54
    stdout
    0.53
    altezza
    0.53
    performance
    0.51
    Dc
    0.51
    
    0.51
    POSITIVE LOGITS
     margin
    1.09
     margins
    0.97
     EdgeInsets
    0.94
     Margin
    0.90
     marginTop
    0.89
    margin
    0.89
    Margin
    0.84
     Padding
    0.83
     margen
    0.82
    marginTop
    0.82
    Activations Density 0.017%

    No Known Activations