© 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. 10-GEMMASCOPE-RES-131K
    7. 19513
    Prev
    Next
    INDEX
    Explanations

    height and width

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

    The neuron fires on numeric literals or tokens representing width/height dimension parameters in code.

    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
     ブログ
    -1.63
    
    -1.57
     μας
    -1.47
     cortado
    -1.43
    Succeed
    -1.42
     INFORMACIÓN
    -1.41
    čna
    -1.41
     alliés
    -1.41
     what
    -1.40
     réunions
    -1.40
    POSITIVE LOGITS
     The
    1.76
     is
    1.64
     "
    1.62
    4
    1.61
    0
    1.59
    phemy
    1.57
    8
    1.44
     è
    1.37
    犄
    1.34
    只不过
    1.32
    Activations Density 0.008%

    No Known Activations