© 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. 22-GEMMASCOPE-RES-131K
    4. 69127
    Prev
    Next
    INDEX
    Explanations

    DNA sequences and molecular biology

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

    DNA/RNA nucleotide sequences, particularly focusing on combinations of letters like ATCG.

    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_22/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
     of
    -1.88
     an
    -1.40
     have
    -1.34
     diskusi
    -1.34
     on
    -1.33
     berguna
    -1.29
     bagus
    -1.29
     things
    -1.26
    Even
    -1.24
     but
    -1.23
    POSITIVE LOGITS
    לין
    1.37
    暧
    1.34
    Править
    1.25
     wana
    1.24
     kube
    1.21
     کرت
    1.20
    boutin
    1.20
     nintendo
    1.19
     トレーナー
    1.16
     tinder
    1.16
    Activations Density 0.018%

    No Known Activations