© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 49887
    Prev
    Next
    INDEX
    Explanations

    Getty Images

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

    This neuron detects occurrences of “Getty Images” photo credit/source attributions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    vedať
    -0.86
     REN
    -0.82
    鐲
    -0.78
    две
    -0.78
    geox
    -0.77
     NSM
    -0.76
    Groetjes
    -0.76
     CSM
    -0.75
     opa
    -0.74
    ্যান
    -0.74
    POSITIVE LOGITS
     images
    1.91
     Images
    1.83
    Images
    1.67
     image
    1.65
    images
    1.54
    image
    1.52
     Image
    1.39
     imágenes
    1.35
    Image
    1.25
     imagens
    1.24
    Activations Density 0.009%

    No Known Activations