© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79838
    Prev
    Next
    INDEX
    Explanations

    physiology research

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

    terms and references related to scientific journals and publications in the field of physiology.

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

    The neuron strongly fires on bibliographic citation details—journal names, volume and page numbers, and related reference metadata.

    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
    又一次
    -0.99
    再一次
    -0.96
    Continua
    -0.93
     Bewußt
    -0.89
     掃除
    -0.89
     chromosomal
    -0.89
    越是
    -0.88
    告诉你
    -0.88
     "//
    -0.88
     transcendent
    -0.88
    POSITIVE LOGITS
    balleur
    1.08
    issão
    1.07
     perubahan
    1.06
     water
    1.06
     changes
    1.06
    đèn
    1.05
    这些
    1.05
     Aging
    1.05
    说
    1.02
     measurements
    1.01
    Activations Density 0.216%

    No Known Activations