© 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. 71363
    Prev
    Next
    INDEX
    Explanations

    DNA sequences, binding, repair

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

    The neuron detects mentions of DNA within scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The main thing this neuron does is detect occurrences of the term “DNA.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    乆
    -3.06
    戋
    -2.75
    Of
    -2.67
     Then
    -2.58
    This
    -2.48
    咝
    -2.47
    敉
    -2.45
     hadapan
    -2.38
    It
    -2.36
     are
    -2.33
    POSITIVE LOGITS
     were
    2.56
     tetapi
    2.47
     Herausforderung
    2.30
     In
    2.25
     Однако
    2.23
    ﮕ
    2.23
     rígido
    2.22
     וב
    2.13
    ztes
    2.11
    𐌻
    2.11
    Activations Density 0.021%

    No Known Activations