© 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. 8509
    Prev
    Next
    INDEX
    Explanations

    waiting for

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

    This neuron strongly activates on the preposition “for,” particularly when it’s part of “wait for” or similar constructions indicating waiting or pending events.

    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
    s
    -3.45
    0
    -2.72
    1
    -2.67
    4
    -2.66
    3
    -2.64
    k
    -2.56
    5
    -2.50
    6
    -2.41
    g
    -2.33
    9
    -2.30
    POSITIVE LOGITS
    ᕱ
    2.06
     konkrét
    2.06
     penyanyi
    2.05
    瓛
    2.05
     someone
    2.02
     it
    2.00
     a
    1.97
    鶿
    1.96
    ائج
    1.96
     tussen
    1.93
    Activations Density 0.009%

    No Known Activations