© 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. 112378
    Prev
    Next
    INDEX
    Explanations

    DNA sequences and alphanumeric identifiers

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

    DNA, RNA, or genetic sequences containing nucleotide base pairs (like ACGT).

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

    The neuron strongly responds to contiguous runs of the four DNA bases (A, C, G, T), i.e. to nucleotide sequence k-mers.

    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
     that
    -1.66
    Typically
    -1.63
    abbaye
    -1.52
    Neither
    -1.48
     encantador
    -1.45
    Since
    -1.42
    Before
    -1.41
    Usually
    -1.41
    Generally
    -1.41
     when
    -1.34
    POSITIVE LOGITS
     nuove
    1.63
    6
    1.41
     arro
    1.41
    亖
    1.40
    та
    1.40
    ités
    1.38
     finally
    1.38
    洒落
    1.37
     revis
    1.36
    荩
    1.35
    Activations Density 0.023%

    No Known Activations