© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8529
    Prev
    Next
    INDEX
    Explanations

    numbers containing 6

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

    The neuron strongly activates on the digit “6,” i.e. occurrences of the character 6 in numeric strings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ing
    -2.64
     akin
    -2.55
    when
    -2.44
     subsequently
    -2.28
     chiefly
    -2.23
    {
    -2.17
     alongside
    -2.16
    ''
    -2.16
    餮
    -2.14
     comprising
    -2.11
    POSITIVE LOGITS
     แต่
    2.94
    ఌ
    2.78
    ();//
    2.78
    蹰
    2.77
     unſ
    2.77
    鮡
    2.73
     greateſt
    2.70
    퐿
    2.66
    は
    2.66
    で
    2.64
    Activations Density 0.328%

    No Known Activations