© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44187
    Prev
    Next
    INDEX
    Explanations

    untreated groups or patients

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

    The neuron detects experimental control groups in scientific studies, particularly focusing on "untreated," "control," and "no treatment" conditions.

    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
     distingu
    -1.40
    ≈
    -1.29
     другие
    -1.23
     nonostante
    -1.23
     percep
    -1.21
     
    -1.20
     ´
    -1.19
     ...
    -1.17
     WHILE
    -1.17
     beetje
    -1.17
    POSITIVE LOGITS
     Each
    1.47
     Additional
    1.38
     There
    1.35
     dijual
    1.32
     Depending
    1.28
    These
    1.28
    There
    1.28
     Those
    1.27
     Jetzt
    1.26
    detek
    1.25
    Activations Density 0.116%

    No Known Activations