© 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. 22-GEMMASCOPE-RES-131K
    7. 71236
    Prev
    Next
    INDEX
    Explanations

    introductions and reviews

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

    The neuron activates on standalone numerals, essentially detecting number tokens 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
    unfortunately
    -1.15
     különböző
    -1.09
    Unfortunately
    -1.08
     azonban
    -0.99
    itteet
    -0.95
    However
    -0.93
     signification
    -0.93
    Indonesia
    -0.88
     Unfortunately
    -0.88
     allerdings
    -0.88
    POSITIVE LOGITS
     overall
    1.00
    észetes
    0.88
     conclusion
    0.86
    guntas
    0.83
     it
    0.82
     []:
    0.81
     generally
    0.80
     and
    0.80
    munk
    0.80
     if
    0.79
    Activations Density 0.010%

    No Known Activations