© 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. 32605
    Prev
    Next
    INDEX
    Explanations

    p-values and statistical significance

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

    The neuron activates on numeric tokens (e.g. counts, measurement values, p-values, and other numbers) 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
    Ђ
    -0.88
    odyne
    -0.85
     atomic
    -0.83
     fine
    -0.81
     õ
    -0.80
    ＿
    -0.80
     ТА
    -0.79
     but
    -0.79
     vont
    -0.77
     critic
    -0.77
    POSITIVE LOGITS
    時には
    0.88
     kênh
    0.87
     apoy
    0.85
     anteriorly
    0.84
    sprozess
    0.84
     trượt
    0.82
    IsPostBack
    0.81
    ifts
    0.77
    umns
    0.76
     outstretched
    0.76
    Activations Density 0.008%

    No Known Activations