© 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. 61127
    Prev
    Next
    INDEX
    Explanations

    pictures or visual content

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

    The neuron detects occurrences of the word “picture” (especially its plural form “pictures”), i.e. references to photos.

    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
    s
    -3.06
    所有
    -3.00
    We
    -2.88
    ３
    -2.70
    (
    -2.70
    4
    -2.56
    一個
    -2.53
    ５
    -2.48
    \
    -2.48
    As
    -2.48
    POSITIVE LOGITS
    </h3>
    3.88
    鉏
    2.89
     Hinblick
    2.69
     Gegensatz
    2.66
    umbnail
    2.64
    
    2.64
    羕
    2.56
    
    2.52
    鴣
    2.48
    歘
    2.48
    Activations Density 0.010%

    No Known Activations