© 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. 102665
    Prev
    Next
    INDEX
    Explanations

    time and change

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

    This neuron responds to very common high‐frequency English words—especially function words (like “the,” “of,” “in,” “and”) and common adverbs or intensifiers (“how,” “much,” “has,” “changed”).

    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
    ṇ
    -0.98
     bunu
    -0.96
    реи
    -0.95
    Dbg
    -0.93
    Medieval
    -0.92
    Museums
    -0.92
    ือง
    -0.92
     indah
    -0.91
    hody
    -0.91
    lllll
    -0.90
    POSITIVE LOGITS
     times
    3.25
     things
    2.38
     technology
    2.34
     changes
    2.31
    Times
    2.25
    times
    2.05
     Times
    2.00
     change
    1.86
     time
    1.80
    Changes
    1.80
    Activations Density 0.078%

    No Known Activations