© 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. 34-GEMMASCOPE-RES-131K
    4. 116877
    Prev
    Next
    INDEX
    Explanations

    saving to disk or file

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

    This neuron consistently activates on occurrences of the token “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_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
     version
    -0.95
     crucial
    -0.94
      
    -0.90
    ❉
    -0.90
    ↵
    -0.84
    东西
    -0.84
    美味し
    -0.82
    における
    -0.81
     données
    -0.80
     crunch
    -0.80
    POSITIVE LOGITS
     disk
    2.66
    disk
    2.09
    Disk
    1.90
     disc
    1.59
     Disk
    1.59
     filesystem
    1.57
    DISK
    1.55
     memory
    1.44
    disc
    1.43
     disks
    1.43
    Activations Density 0.175%

    No Known Activations