© 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. 34-GEMMASCOPE-RES-131K
    4. 97919
    Prev
    Next
    INDEX
    Explanations

    biological stains and dyes

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

    fluorescent dyes and chemical staining compounds used in laboratory imaging and analysis.

    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
     Clarence
    -0.82
     Wittenberg
    -0.77
     stoned
    -0.75
    Clarence
    -0.74
    lsch
    -0.73
    oudre
    -0.72
    ٥
    -0.72
    ↥
    -0.72
    onDestroy
    -0.72
    Decoration
    -0.71
    POSITIVE LOGITS
     staining
    1.27
     stain
    1.16
     dye
    1.10
     stains
    1.07
     intercal
    1.03
     stained
    1.02
     nucleic
    0.96
     Staining
    0.88
     Nucleic
    0.87
    stained
    0.85
    Activations Density 0.061%

    No Known Activations