© 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. 10053
    Prev
    Next
    INDEX
    Explanations

    programming data structures

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

    the opening parenthesis in R function calls, particularly when creating data structures like lists or data frames.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    </h4>
    -1.60
     evil
    -1.57
    3
    -1.55
     Erinner
    -1.53
     damaligen
    -1.51
    熟悉的
    -1.48
     Aussehen
    -1.46
     scatola
    -1.46
     ihren
    -1.45
     We
    -1.45
    POSITIVE LOGITS
    😲
    1.92
    🫡
    1.77
    🍻
    1.70
    🤙
    1.68
    🌞
    1.63
     fii
    1.60
    🤭
    1.59
    🤨
    1.59
     thema
    1.59
     coton
    1.58
    Activations Density 0.003%

    No Known Activations