© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115658
    Prev
    Next
    INDEX
    Explanations

    currency amounts and weights

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

    The neuron strongly activates on numeric tokens (e.g. measurements, counts, dates, monetary values).

    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
     waving
    -0.76
     waved
    -0.75
    artet
    -0.74
     Raptor
    -0.73
     synapses
    -0.72
    fattning
    -0.71
     indeb
    -0.70
    닳
    -0.70
    层的
    -0.67
    urnum
    -0.67
    POSITIVE LOGITS
     odd
    0.81
    эм
    0.80
     definiciones
    0.79
     Pioneer
    0.73
     teorías
    0.72
    Pioneer
    0.72
    ब्
    0.72
     Arquite
    0.71
     PV
    0.71
    entr
    0.70
    Activations Density 0.028%

    No Known Activations