© 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. 123728
    Prev
    Next
    INDEX
    Explanations

    widespread pain, tinnitus, grinding

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

    anatomical terms related to joints, muscles, and medical conditions, particularly in technical medical texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     on
    -1.15
     veck
    -1.12
    astia
    -1.08
     äm
    -1.07
     ipa
    -1.07
    >@
    -1.07
     :"
    -1.07
     danske
    -1.06
     for
    -1.05
    while
    -1.05
    POSITIVE LOGITS
    öld
    1.23
     your
    1.23
     barva
    1.21
     koszulka
    1.20
     turísticos
    1.17
    yaratan
    1.13
    providedIn
    1.13
     systému
    1.12
     primeras
    1.11
     ständig
    1.11
    Activations Density 0.112%

    No Known Activations