© 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. 82486
    Prev
    Next
    INDEX
    Explanations

    age group demographics

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

    The neuron activates on numeric tokens—counts, statistics, and other 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
     अव
    -0.81
     exemplo
    -0.75
     reflexión
    -0.74
     Brewers
    -0.73
     یک
    -0.72
    前任
    -0.72
     Exclusion
    -0.70
    ureen
    -0.68
     प्रकार
    -0.68
    ляр
    -0.68
    POSITIVE LOGITS
     ages
    2.31
    Ages
    1.72
     Ages
    1.71
     aged
    1.58
     age
    1.56
     between
    1.49
    ages
    1.47
     persons
    1.08
     edades
    1.05
     berusia
    1.05
    Activations Density 0.056%

    No Known Activations