© 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. 22-GEMMASCOPE-RES-131K
    7. 64928
    Prev
    Next
    INDEX
    Explanations

    first antibody production

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

    scientific text in academic papers, particularly in methods and results sections.

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

    The neuron strongly activates on passages describing scientific studies or experimental procedures in academic research papers.

    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
     promociones
    -1.54
     cojín
    -1.38
     правительства
    -1.38
     функция
    -1.34
     السياس
    -1.34
    aktionen
    -1.31
    ஒ
    -1.29
     acuario
    -1.26
     silikon
    -1.25
     ส์
    -1.24
    POSITIVE LOGITS
     recently
    1.67
     currently
    1.56
     will
    1.42
     we
    1.35
     our
    1.34
     Currently
    1.30
     zatím
    1.23
    亟
    1.19
     upcoming
    1.19
    瘢
    1.14
    Activations Density 0.304%

    No Known Activations