© 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. 74261
    Prev
    Next
    INDEX
    Explanations

    dimensions: width, height

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

    The neuron fires on CSS “width” declarations—especially in media queries or style rules specifying min/max widths.

    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
     if
    -2.17
    Because
    -1.92
    ’，
    -1.73
     If
    -1.69
     will
    -1.60
    Since
    -1.52
    Only
    -1.51
    ка
    -1.48
    Much
    -1.48
     because
    -1.48
    POSITIVE LOGITS
     싶
    1.63
    itization
    1.63
    vereignty
    1.49
    obacz
    1.48
     vêtement
    1.46
     anderem
    1.45
    🫂
    1.42
    
    1.40
    ),
    1.40
    krieg
    1.38
    Activations Density 0.002%

    No Known Activations