© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 16147
    Prev
    Next
    INDEX
    Explanations

    now + current state

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

    This neuron primarily detects the temporal adverb “now.”

    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
     parfois
    -1.30
     then
    -1.28
    時には
    -1.25
    ופן
    -1.23
    schon
    -1.20
    휀
    -1.20
     CONTIN
    -1.17
     toujours
    -1.15
     it
    -1.13
     unchanged
    -1.13
    POSITIVE LOGITS
     också
    1.48
    Now
    1.41
    ;
    1.34
    Even
    1.30
     möjlighet
    1.28
     også
    1.27
    х
    1.27
    re
    1.27
     більш
    1.25
     istället
    1.24
    Activations Density 0.029%

    No Known Activations