© 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. 130869
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to numeric tokens (digits or numbers) embedded in code or markup.

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

    HTML tags and attributes

    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
     to
    -1.84
     también
    -1.08
    也会
    -1.07
     també
    -1.07
     微信
    -1.06
     OGSÅ
    -1.05
     asiática
    -1.04
    のではないか
    -1.02
    にならない
    -1.02
    に行って
    -1.01
    POSITIVE LOGITS
    –
    1.10
    機能
    1.10
    鈑
    1.04
    
    1.04
    1.02
    TagHelpers
    1.00
    1.00
     vectores
    1.00
    
    0.99
    catalytic
    0.98
    Activations Density 0.000%

    No Known Activations