© 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. 77630
    Prev
    Next
    INDEX
    Explanations

    inclusion and disability

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

    The main thing this neuron does is detect numeric tokens and date‐like expressions (e.g. years, counts, and other numbers).

    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
     hubiese
    -0.81
     allowing
    -0.77
     allows
    -0.76
     minY
    -0.75
    There
    -0.74
    During
    -0.73
    ✗
    -0.73
     didik
    -0.71
     may
    -0.70
     comes
    -0.70
    POSITIVE LOGITS
     CBR
    0.95
     inclusive
    0.94
     inclusion
    0.88
     Inclusive
    0.86
    饵
    0.84
    Inclusive
    0.82
     PERSONS
    0.81
    HideFlags
    0.80
     الأشخاص
    0.79
     WASH
    0.79
    Activations Density 0.023%

    No Known Activations