© 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. 104172
    Prev
    Next
    INDEX
    Explanations

    scientific measurement studies

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

    scientific terms related to laboratory testing methods, biological assays, and pharmacological studies.

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

    The neuron detects specialized biomedical and pharmacological technical terms—especially assay names, toxicity/genotoxicity measures, pharmacokinetic and bioavailability metrics, and other multi-syllabic Latin/Greek-derived laboratory jargon.

    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
    matical
    -1.52
    eload
    -1.51
    が
    -1.44
    tled
    -1.40
     esfuer
    -1.38
     однако
    -1.34
    itization
    -1.32
    сыз
    -1.32
    がなく
    -1.32
    まさか
    -1.30
    POSITIVE LOGITS
     about
    1.81
     if
    1.43
     my
    1.41
     analysis
    1.41
     determine
    1.34
     also
    1.30
     and
    1.27
    this
    1.25
     now
    1.25
     of
    1.21
    Activations Density 0.347%

    No Known Activations