© 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. 41701
    Prev
    Next
    INDEX
    Explanations

    cyclin D compounds

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

    biochemical and molecular biology terms, particularly protein and chemical compound names.

    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
    f
    -2.16
     باسلام
    -2.09
    こんな感じで
    -1.83
    d
    -1.83
    NESSEE
    -1.80
     augusti
    -1.76
    es
    -1.75
    ging
    -1.75
    fertigt
    -1.73
     також
    -1.70
    POSITIVE LOGITS
     když
    1.73
     您
    1.73
    .
    1.70
    琊
    1.70
     Cuando
    1.66
    }
    
    
    1.65
    érôme
    1.55
     Hinsicht
    1.54
    }{
    1.52
    biega
    1.51
    Activations Density 0.257%

    No Known Activations