© 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. 61047
    Prev
    Next
    INDEX
    Explanations

    surgical procedures and body modification

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

    medical or cosmetic body modification procedures such as circumcision, vasectomy, ligation, and piercings.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ane
    -1.60
    ut
    -1.54
    E
    -1.52
     this
    -1.49
    {
    -1.45
    ar
    -1.44
    p
    -1.39
    ts
    -1.38
    c
    -1.38
    us
    -1.36
    POSITIVE LOGITS
    enuta
    1.43
     sabias
    1.38
    ktory
    1.37
     the
    1.34
     kosme
    1.30
     encantador
    1.23
    ICIONES
    1.23
    ič
    1.23
    führende
    1.23
     preocupado
    1.22
    Activations Density 0.059%

    No Known Activations