© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111058
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terms

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

    scientific text with italicized taxonomic names.

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

    This neuron detects typographic or markup emphasis markers (e.g. HTML tags like `<i>` or asterisks `*`).

    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
     for
    -2.02
     this
    -1.94
     it
    -1.84
     at
    -1.80
     or
    -1.78
     these
    -1.70
     our
    -1.64
     of
    -1.58
     those
    -1.56
     your
    -1.55
    POSITIVE LOGITS
     إحدى
    1.70
     peintures
    1.65
    ↵
    1.64
     \
    1.60
    presumably
    1.59
     ‘’
    1.59
     silber
    1.55
    payable
    1.55
    KommentareTeilen
    1.55
    -*
    1.55
    Activations Density 0.002%

    No Known Activations