© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30061
    Prev
    Next
    INDEX
    Explanations

    reschedule or postpone

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

    The neuron is tuned to detect numeric tokens and quantities (i.e. digit sequences and numbers).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    introdu
    -0.82
     Stopping
    -0.80
    retired
    -0.79
     quitting
    -0.77
     dyna
    -0.76
     αὐ
    -0.74
     CrossRef
    -0.73
     gogh
    -0.71
     револю
    -0.71
    dyna
    -0.71
    POSITIVE LOGITS
     rescheduled
    3.88
     reschedule
    3.42
     postponed
    2.53
     postponement
    2.17
     postpone
    2.03
     перене
    1.95
     postpon
    1.91
     res
    1.82
     rearranged
    1.73
    延期
    1.70
    Activations Density 0.026%

    No Known Activations