© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60551
    Prev
    Next
    INDEX
    Explanations

    economic and statistical terms

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

    The neuron is primarily responsive to numeric tokens—that is, to numbers and digit sequences 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
    汕
    -0.79
    casian
    -0.78
     مؤ
    -0.74
     Marinette
    -0.73
    ByVersion
    -0.73
     Factors
    -0.72
    엎
    -0.71
    demografi
    -0.70
    陸軍
    -0.69
     integrals
    -0.68
    POSITIVE LOGITS
     elasticity
    1.14
     elastici
    0.91
     Elasticity
    0.89
    参数
    0.88
    rho
    0.84
     parámetros
    0.84
    elastic
    0.83
     parameter
    0.82
     phi
    0.79
    くらいで
    0.77
    Activations Density 0.010%

    No Known Activations