© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 69125
    Prev
    Next
    INDEX
    Explanations

    generate followed by specific nouns

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

    The neuron spotlights occurrences of “generate” (and its variants like “generator,” “generates,” etc.) in code or documentation.

    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
    鰨
    -2.77
    𓋼
    -2.73
     mân
    -2.66
    ⡑
    -2.55
    that
    -2.53
    鹛
    -2.50
    ી
    -2.50
    慙
    -2.44
    ᨕ
    -2.42
    횃
    -2.39
    POSITIVE LOGITS
     –
    3.56
     —
    3.27
     of
    3.14
     and
    3.03
     \
    2.63
     ‘‘
    2.56
    ,
    2.33
    霂
    2.31
     ""){
    2.30
    
    2.27
    Activations Density 0.064%

    No Known Activations