© 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. 10-GEMMASCOPE-RES-131K
    4. 87395
    Prev
    Next
    INDEX
    Explanations

    visual output and display

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

    This neuron activates on terms related to showing or rendering visual output—e.g., “display,” “displays,” “displaying,” “visual,” “visualize,” and similar words.

    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
    ثيق
    -1.37
     they
    -1.36
     \
    -1.30
     Either
    -1.29
    L
    -1.27
     Now
    -1.27
    UnitTesting
    -1.25
    X
    -1.24
     nieruch
    -1.24
    ToMany
    -1.23
    POSITIVE LOGITS
    毉
    1.51
    dekor
    1.34
     erhi
    1.34
    𓂀
    1.34
    emporio
    1.33
    ~"
    1.31
    prayer
    1.30
    躂
    1.28
    fotografia
    1.28
     cadáver
    1.28
    Activations Density 0.133%

    No Known Activations