© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75077
    Prev
    Next
    INDEX
    Explanations

    mathematical division

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

    The neuron selectively activates on numeric tokens (multi‐digit and decimal 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
    久し
    -1.93
    さぁ
    -1.77
    あぁ
    -1.63
    niño
    -1.59
    マジで
    -1.57
    もうすぐ
    -1.56
    久しぶりに
    -1.55
    ❢
    -1.55
    ほうがいい
    -1.55
    XDD
    -1.54
    POSITIVE LOGITS
    GRAFÍA
    1.79
     (
    1.78
    —
    1.52
     Grüßen
    1.47
    to
    1.45
    déric
    1.41
     they
    1.35
     get
    1.30
    ,
    1.30
     all
    1.30
    Activations Density 0.042%

    No Known Activations