© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21234
    Prev
    Next
    INDEX
    Explanations

    waiting / awaiting things

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

    The neuron consistently fires on words and short phrases that signal expectation of something forthcoming—e.g. “waiting,” “awaiting,” or “to …” constructions indicating an upcoming event or deliverable.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    }{
    -1.52
    櫚
    -1.47
     xxiii
    -1.41
    榈
    -1.38
    ꦏ
    -1.38
    多年
    -1.37
     attivo
    -1.36
    詎
    -1.36
     xxvi
    -1.34
     Abgerufen
    -1.34
    POSITIVE LOGITS
     awaits
    1.50
    ୩
    1.41
    ?
    1.41
    跟他
    1.35
     they
    1.32
    櫛
    1.31
    引起了
    1.30
     ;)
    1.30
     rendent
    1.29
    诠
    1.28
    Activations Density 0.013%

    No Known Activations