© 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. 81006
    Prev
    Next
    INDEX
    Explanations

    political figures and government policy areas

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

    The neuron specializes in spotting numeric tokens—particularly multi‐digit sequences such as highway or year 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
     Tangerang
    -0.86
     formed
    -0.80
    ازات
    -0.68
    RequestId
    -0.68
     образования
    -0.68
     menurunkan
    -0.68
    folders
    -0.67
     تامین
    -0.66
    ^-
    -0.66
    packet
    -0.65
    POSITIVE LOGITS
    ispiel
    0.81
     Aki
    0.81
     MPP
    0.77
    řevě
    0.75
     прекрасно
    0.71
    enix
    0.71
    nosaurus
    0.70
     pojaw
    0.69
     Blacks
    0.69
     yapan
    0.68
    Activations Density 0.031%

    No Known Activations