© 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. 13461
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with parentheses

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

    This neuron activates on numeric tokens (especially multi-digit numbers) 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
     support
    -1.20
     and
    -1.15
     park
    -1.09
     etc
    -1.09
     ans
    -1.05
    CloseOperation
    -1.05
     test
    -1.04
     ie
    -1.03
     την
    -1.03
     And
    -1.02
    POSITIVE LOGITS
     courrier
    1.44
     certificat
    1.44
     curé
    1.36
     saut
    1.35
     saus
    1.34
     compromis
    1.32
     teras
    1.31
    宬
    1.31
     Recuper
    1.30
     asfal
    1.30
    Activations Density 0.011%

    No Known Activations