© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91592
    Prev
    Next
    INDEX
    Explanations

    kidney disease

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

    URLs, file paths, and web-related formatting elements like HTML tags and code comments.

    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_34/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
    варя
    -0.90
     gitu
    -0.88
     материал
    -0.87
    ")==
    -0.87
     kentang
    -0.83
     alat
    -0.83
    )}{
    -0.83
     arv
    -0.82
    ÑOS
    -0.81
     intress
    -0.79
    POSITIVE LOGITS
    йтесь
    0.90
    ↵↵↵
    0.84
     Astral
    0.76
     soutenir
    0.75
     aerospace
    0.75
     lautet
    0.74
    アイデア
    0.73
    aseous
    0.73
     hurrying
    0.73
     yahoo
    0.72
    Activations Density 0.002%

    No Known Activations