© 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. 91211
    Prev
    Next
    INDEX
    Explanations

    DNA bases and nucleotides

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

    DNA and genetic sequence notations.

    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
    concurrency
    -0.83
     Madsen
    -0.79
    励志
    -0.71
     toolStrip
    -0.70
     ilgili
    -0.70
    =(-
    -0.69
     Bảo
    -0.69
    blestone
    -0.69
    rature
    -0.69
    ナンバー
    -0.67
    POSITIVE LOGITS
     aden
    1.34
     Aden
    1.32
     nucleotide
    1.28
     nucleotides
    1.22
    Aden
    1.13
     Guan
    1.12
     bases
    1.09
     DNA
    1.08
    DNA
    1.01
    aden
    0.99
    Activations Density 0.042%

    No Known Activations