© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130441
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric literal tokens (integer or decimal numbers) embedded in code or markup.

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

    For your vehicles

    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
    くれた
    -1.08
     acreditar
    -1.01
     laranja
    -1.01
    
    -1.00
     powy
    -0.97
    တ်
    -0.93
     Grundlage
    -0.91
     pattern
    -0.91
     entraîner
    -0.90
     ścian
    -0.90
    POSITIVE LOGITS
     for
    1.23
     froide
    1.04
    gypte
    1.00
     UNTIL
    0.96
    ův
    0.95
    naden
    0.94
    MathML
    0.94
     معنی
    0.94
    ονται
    0.93
     минера
    0.93
    Activations Density 0.001%

    No Known Activations