© 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. 34-GEMMASCOPE-RES-131K
    7. 108348
    Prev
    Next
    INDEX
    Explanations

    when clauses

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

    This neuron fires on the subordinating conjunction “when,” i.e. the word “when” introducing temporal clauses.

    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
     a
    -1.57
    ご注文
    -1.09
    uating
    -1.01
    そのため
    -0.98
     ausdrücklich
    -0.96
     geographical
    -0.96
     Tradu
    -0.95
    痛み
    -0.93
     classical
    -0.92
     offens
    -0.91
    POSITIVE LOGITS
     they
    1.59
     in
    1.53
     you
    1.40
     on
    1.31
     it
    1.27
     its
    1.22
     asleep
    1.09
     awake
    1.09
     estão
    1.05
     pertama
    1.05
    Activations Density 0.061%

    No Known Activations