© 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. 119821
    Prev
    Next
    INDEX
    Explanations

    emphatic programming contexts

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

    the arrow operator (`->`) used for accessing members of pointers in C/C++ code.

    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
     unrelenting
    -2.80
     multifaceted
    -2.52
     which
    -2.38
     intensely
    -2.34
     only
    -2.31
     unparalleled
    -2.30
     enticing
    -2.30
     exquisitely
    -2.28
     burgeoning
    -2.27
     enhances
    -2.22
    POSITIVE LOGITS
     Dinas
    2.66
     adorned
    2.61
     sooo
    2.59
     😁
    2.55
     REALLY
    2.52
     soooo
    2.52
     ridiculously
    2.52
     acclaimed
    2.50
     exceedingly
    2.47
     magnificent
    2.45
    Activations Density 0.003%

    No Known Activations