© 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. 34-GEMMASCOPE-RES-131K
    7. 76318
    Prev
    Next
    INDEX
    Explanations

    genomic, genome, annotation

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

    code syntax and programming-related text, particularly in contexts like file headers, imports, and code snippets.

    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
    镯
    -0.92
    oidal
    -0.87
    (:,:,
    -0.86
    uance
    -0.82
     body
    -0.81
    手镯
    -0.80
    ]-'
    -0.79
     Differenti
    -0.79
    zoned
    -0.79
    𓂂
    -0.79
    POSITIVE LOGITS
     exon
    1.16
     barcode
    1.05
     genomic
    1.05
     genome
    1.05
    genome
    1.03
     Genome
    1.02
    Anno
    1.01
     Genomic
    1.01
    anno
    1.00
     المعلومات
    1.00
    Activations Density 0.068%

    No Known Activations