© 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. 99168
    Prev
    Next
    INDEX
    Explanations

    topic headings and specific terms

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

    The neuron primarily activates on numeric tokens (multi‐digit numbers, dates, times, statistics) in the text.

    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
     lamenta
    -0.77
     unmistakable
    -0.74
    挡
    -0.73
     Stockton
    -0.72
    不但
    -0.71
     $^{
    -0.71
    closeConnection
    -0.71
    ristiano
    -0.71
     получается
    -0.69
     abandon
    -0.68
    POSITIVE LOGITS
    generally
    0.93
     PyTuple
    0.90
     Mercedes
    0.87
    PN
    0.86
    اشته
    0.85
    ;}
    0.84
     العاصمة
    0.81
    PACS
    0.79
    ниципа
    0.79
    Purchase
    0.79
    Activations Density 0.004%

    No Known Activations