© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68193
    Prev
    Next
    INDEX
    Explanations

    asking and answering questions

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

    This neuron strongly activates on the word “to.”

    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
     philippe
    -1.23
    眼前的
    -1.19
    眼下
    -1.17
    他也
    -1.15
    ниця
    -1.13
     oczeki
    -1.12
     ganador
    -1.11
    alo
    -1.11
     tucson
    -1.09
     dictionnaire
    -1.09
    POSITIVE LOGITS
     information
    1.52
     answers
    1.38
     their
    1.33
     answer
    1.32
    そんな
    1.25
     talked
    1.20
     analysis
    1.20
    شفى
    1.18
    關於
    1.17
    Плюсы
    1.16
    Activations Density 0.048%

    No Known Activations