© 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. 22-GEMMASCOPE-RES-131K
    7. 80072
    Prev
    Next
    INDEX
    Explanations

    code, data, life, sperm

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

    code or technical elements like brackets, XML tags, and syntax indicators in programming contexts.

    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_22/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
     already
    -1.03
     afterwards
    -1.02
     afterward
    -0.95
     either
    -0.95
     there
    -0.91
     vyrá
    -0.91
     이미
    -0.91
     Gnade
    -0.90
     카드
    -0.89
    Amigo
    -0.87
    POSITIVE LOGITS
    倏
    0.96
    ranton
    0.93
    着自己的
    0.91
    ท
    0.91
    midos
    0.90
    さんの
    0.89
     guste
    0.88
    reportWebVitals
    0.85
     parha
    0.84
     ट
    0.84
    Activations Density 0.062%

    No Known Activations