© 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. 65071
    Prev
    Next
    INDEX
    Explanations

    ATP-binding cassette, fibrinogen, runner, Davis

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

    scientific or technical terms, particularly biochemical terms, protein names, and molecular components.

    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
    when
    -2.02
    グルト
    -1.78
    People
    -1.73
    ⁈
    -1.73
    诶
    -1.67
     RSITY
    -1.63
    Having
    -1.63
    Putting
    -1.59
    Taking
    -1.58
    　↓
    -1.57
    POSITIVE LOGITS
     to
    1.95
    ,(
    1.72
    si
    1.70
    äume
    1.67
    ți
    1.63
    िक
    1.62
     book
    1.62
     senza
    1.61
    ”,
    1.58
     kinda
    1.58
    Activations Density 0.087%

    No Known Activations