© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57043
    Prev
    Next
    INDEX
    Explanations

    ongoing process or efforts

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

    The neuron is specialized to detect occurrences of the word “ongoing.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     recently
    -1.27
     pakan
    -1.19
     jums
    -1.18
     commencent
    -1.06
     laim
    -1.05
    Oltre
    -1.03
    Daha
    -1.02
    ungkapkan
    -1.02
    עת
    -1.02
    目前的
    -1.01
    POSITIVE LOGITS
     efforts
    1.40
     saga
    1.35
     commitment
    1.29
     Efforts
    1.27
     effort
    1.25
     процессе
    1.21
     and
    1.19
     Presence
    1.17
     процесса
    1.17
     debate
    1.14
    Activations Density 0.025%

    No Known Activations