© 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. 67664
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    The neuron activates on standalone numeric tokens (numbers and digits).

    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
    ⭐⭐
    -1.08
     mété
    -1.08
    pergillus
    -1.03
    $$
    
    -1.02
    🦉
    -0.96
     pokoju
    -0.96
     оружия
    -0.94
    wykle
    -0.94
     artistes
    -0.94
    cended
    -0.93
    POSITIVE LOGITS
     установки
    0.91
    efes
    0.90
    essoal
    0.88
    ramienta
    0.83
    プス
    0.82
    rédients
    0.82
     &
    0.82
     Plin
    0.82
    人都
    0.81
    只需要
    0.81
    Activations Density 0.021%

    No Known Activations