© 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. 22-GEMMASCOPE-RES-131K
    7. 10890
    Prev
    Next
    INDEX
    Explanations

    patients, species, children, subjects, products

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

    subjects or participants in scientific/medical studies, particularly when described with numbers.

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

    This neuron detects mentions of patient counts in clinical study descriptions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     anybody
    -1.11
     anyone
    -1.09
     many
    -1.06
     måske
    -1.05
     itself
    -0.99
     banyak
    -0.96
     hjæl
    -0.95
     its
    -0.95
     easier
    -0.94
     tæn
    -0.92
    POSITIVE LOGITS
     have
    1.53
     are
    1.09
     Werkstatt
    1.02
     Dicht
    0.99
    either
    0.97
    Enough
    0.95
    ּוֹ
    0.93
     دارای
    0.93
    וּ
    0.88
     включая
    0.88
    Activations Density 0.103%

    No Known Activations