© 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. 75207
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and formulas

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

    This neuron activates on numeric tokens (numbers, digits, and math‐related numeric expressions) 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
    jedno
    -1.09
     télécommande
    -1.03
    xxi
    -1.00
    madonna
    -1.00
     avancée
    -0.99
     vantagens
    -0.98
    parfum
    -0.98
     romántica
    -0.96
    armani
    -0.95
    NCF
    -0.94
    POSITIVE LOGITS
    ton
    1.15
    ater
    1.08
    V
    1.02
     ボックス
    1.02
    P
    1.00
    ("");
    0.97
    炻
    0.97
    sed
    0.97
    ik
    0.96
    ara
    0.95
    Activations Density 0.026%

    No Known Activations