© 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. 79689
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

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

    The neuron fires on standalone numeric tokens (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
    いただけます
    -1.12
     heilige
    -1.11
     adicionais
    -1.09
    ometry
    -1.05
     fornecer
    -1.04
    pecific
    -1.02
     spezif
    -1.01
     konkrét
    -1.00
    record
    -1.00
    odot
    -0.98
    POSITIVE LOGITS
    Masa
    0.89
     vốn
    0.84
    ucksack
    0.84
     trăm
    0.82
    उत्तर
    0.82
    gimento
    0.80
    wsze
    0.80
    żenia
    0.80
     Torneo
    0.78
     larger
    0.78
    Activations Density 0.030%

    No Known Activations