© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22130
    Prev
    Next
    INDEX
    Explanations

    DNA sequences and motifs

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

    DNA nucleotide sequences and genetic codes.

    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
    媄
    -2.39
     Could
    -2.25
    with
    -2.11
     exceptionally
    -1.93
    m
    -1.91
    🢒
    -1.91
     dalla
    -1.91
    '];?>
    -1.88
     drenaje
    -1.87
    ”;
    -1.86
    POSITIVE LOGITS
    ⵌ
    2.17
    麒
    2.09
    ية
    2.06
     didik
    2.05
    つまり
    1.98
     rivales
    1.93
     incrí
    1.91
     laatste
    1.91
     它
    1.90
    Ꮗ
    1.90
    Activations Density 0.008%

    No Known Activations