© 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. 13170
    Prev
    Next
    INDEX
    Explanations

    show or prove

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

    The neuron fires on numeric tokens (integers or decimals) and math‐mode delimiters, i.e. it detects numbers appearing in mathematical expressions.

    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
     indeed
    -1.08
    や
    -1.03
    tapi
    -1.00
    felizmente
    -0.99
    :^{
    -0.98
     και
    -0.98
    õi
    -0.94
    査
    -0.92
    versial
    -0.92
     other
    -0.90
    POSITIVE LOGITS
     how
    1.29
     августа
    1.14
     then
    1.09
    إنه
    1.09
     июля
    1.05
     questions
    1.02
     Faites
    0.99
     ноября
    0.98
     joten
    0.97
     האם
    0.97
    Activations Density 0.098%

    No Known Activations