© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128439
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric tokens (sequences of digits) in the text.

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

    quantities and units milliliters grams percent

    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
    after
    -1.41
     that
    -1.39
     étrangère
    -1.35
    Nuorodos
    -1.32
    Often
    -1.24
     other
    -1.23
     Kebijakan
    -1.23
     after
    -1.22
     brugt
    -1.17
    viewpager
    -1.16
    POSITIVE LOGITS
     a
    1.55
    を行います
    1.24
    2
    1.12
     rocha
    1.08
     roughly
    1.05
     sviluppo
    1.04
     загру
    1.04
    5
    1.03
    的眼
    1.02
     Brings
    1.02
    Activations Density 0.019%

    No Known Activations