© 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. 22-GEMMASCOPE-RES-131K
    7. 39247
    Prev
    Next
    INDEX
    Explanations

    p-values

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

    The neuron fires on numeric expressions—especially multi‐digit statistics, p-values, percentages, and other measurements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     filós
    -1.06
     how
    -1.00
     ognuno
    -0.97
     jeszcze
    -0.94
     ulteriori
    -0.94
    或許
    -0.93
     działal
    -0.91
    johns
    -0.91
     qualche
    -0.90
    preuve
    -0.87
    POSITIVE LOGITS
    HomeAsUpEnabled
    1.01
    avadoc
    0.90
    祢
    0.89
    稳定的
    0.89
    chini
    0.88
    labili
    0.87
    ilité
    0.87
     régionale
    0.86
    beit
    0.85
    滔
    0.85
    Activations Density 0.004%

    No Known Activations