© 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. 22-GEMMASCOPE-RES-131K
    7. 65181
    Prev
    Next
    INDEX
    Explanations

    second, second plate, or unit

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

    The neuron strongly activates on numeric tokens (integers or decimals), i.e. any standalone numbers or measurements 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_22/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
     masaj
    -0.98
     PriorityQueue
    -0.98
     CONCEPT
    -0.96
     anest
    -0.96
     suav
    -0.93
     ſon
    -0.91
     AUSTIN
    -0.89
     reutiliz
    -0.88
    '[
    -0.87
    madeus
    -0.87
    POSITIVE LOGITS
    Another
    0.91
     sits
    0.81
     for
    0.81
     should
    0.80
    7
    0.80
     ultimate
    0.76
     cilvē
    0.75
     sitter
    0.75
     perplexing
    0.73
    !!!!!
    0.71
    Activations Density 0.034%

    No Known Activations