© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18339
    Prev
    Next
    INDEX
    Explanations

    genomic sequencing and bioinformatics

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

    proteins, DNA, and genomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     соціа
    0.71
    퐫
    0.71
    徭
    0.71
    汽車
    0.64
     паліты
    0.64
     سیاسی
    0.64
    銀行
    0.62
    墘
    0.62
     політи
    0.60
     уголов
    0.60
    POSITIVE LOGITS
     genomic
    1.47
     bioinformatics
    1.39
     genomics
    1.37
     genomes
    1.35
     genome
    1.33
     Bioinformatics
    1.18
     nucleotide
    1.13
     protein
    1.11
     peptide
    1.11
     cDNA
    1.09
    Activations Density 0.093%

    No Known Activations