© 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. 131017
    Prev
    Next
    INDEX
    Explanations

    the neuron activates on numeric tokens (digits and numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    start thread

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     OPPORT
    -1.09
    คม
    -1.09
    Ʃ
    -1.03
     TECHNI
    -1.00
     IMPLEMENTATION
    -0.99
    сай
    -0.98
     CHAIRMAN
    -0.98
     RECIPES
    -0.96
    cosse
    -0.95
     VIDEOT
    -0.95
    POSITIVE LOGITS
    bộ
    1.15
    máy
    1.09
    chaleco
    1.06
     Uniwersyte
    1.05
     it
    1.05
    bảng
    1.02
     unterscheidet
    1.00
    verständnis
    0.99
     Differences
    0.98
     Diciembre
    0.96
    Activations Density 0.012%

    No Known Activations