© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1812
    Prev
    Next
    INDEX
    Explanations

    prime factors or numbers

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

    The neuron detects list delimiters—especially commas (and their trailing spaces) separating numbers.

    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
    ませんでした
    -0.78
    ,'"
    -0.72
     červen
    -0.71
     Gesang
    -0.70
     wreaths
    -0.70
     erecting
    -0.70
     Spect
    -0.69
    شفى
    -0.69
    Serie
    -0.68
     skjø
    -0.68
    POSITIVE LOGITS
     obtained
    1.37
     obtaining
    1.11
    obtained
    1.09
     obtain
    1.05
     Obtain
    0.97
     Obtained
    0.97
    ۱۱
    0.94
     Obtaining
    0.93
     obtains
    0.93
     obtenu
    0.89
    Activations Density 0.031%

    No Known Activations