© 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. 95716
    Prev
    Next
    INDEX
    Explanations

    sprague-dawley rats, sphincter of oddi

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

    scientific notation and numerical measurements in technical/medical texts.

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

    This neuron detects numeric tokens and alphanumeric identifiers (e.g. counts, measurements, or coded labels) in the text.

    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
     you
    -1.48
     is
    -1.30
     favoritas
    -1.23
     berätt
    -1.23
     lyck
    -1.23
     if
    -1.20
     how
    -1.19
     aguacate
    -1.12
     that
    -1.11
     nedan
    -1.09
    POSITIVE LOGITS
    適当
    1.36
     either
    1.23
     geschreven
    1.15
     jeweils
    1.11
    ַּ
    1.10
    だめ
    1.10
    際は
    1.08
    either
    1.08
     entweder
    1.06
    uyla
    1.05
    Activations Density 0.077%

    No Known Activations