© 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. 84389
    Prev
    Next
    INDEX
    Explanations

    psychology and research papers

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

    This neuron activates on numeric tokens—especially numbers in academic references (years, volume and page numbers).

    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
    tingu
    -1.00
     chande
    -0.97
    <0xCE>
    -0.96
     Ом
    -0.95
     rolle
    -0.95
    켰
    -0.94
     drap
    -0.93
     fatale
    -0.93
    guet
    -0.91
     prenn
    -0.90
    POSITIVE LOGITS
     psychologist
    1.37
     fMRI
    1.26
     psychologists
    1.23
     Psychological
    1.21
    Psychological
    1.11
    gridLayout
    1.09
    心理学
    1.09
     APA
    1.03
     testGet
    1.03
    ệu
    1.03
    Activations Density 0.001%

    No Known Activations