© 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. 48438
    Prev
    Next
    INDEX
    Explanations

    JFrame and iframe elements, Romney

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

    The neuron fires on programming identifiers written in camelCase or PascalCase (e.g. Java class/method names, Rails “iframe,” Python “Flipping”).

    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
     explore
    -2.48
    omiast
    -2.48
    氚
    -2.48
     summarize
    -2.47
    corrhi
    -2.42
     årene
    -2.41
    ｰ
    -2.34
     fortfarande
    -2.33
     bäst
    -2.31
    ます
    -2.28
    POSITIVE LOGITS
    
    2.70
    鬭
    2.56
    猡
    2.50
    h
    2.47
    но
    2.41
    ma
    2.41
     Indien
    2.30
    繻
    2.27
     version
    2.23
    $;
    2.23
    Activations Density 0.012%

    No Known Activations