© 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. 10-GEMMASCOPE-RES-131K
    7. 39197
    Prev
    Next
    INDEX
    Explanations

    conditional clauses

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

    This neuron activates on numeric tokens (numbers or numerical 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_10/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
    werden
    -2.02
     rengi
    -1.81
    訁
    -1.80
    ⑉
    -1.77
     eksper
    -1.75
    
    -1.73
    躥
    -1.73
     ujar
    -1.70
     auront
    -1.65
    specifically
    -1.65
    POSITIVE LOGITS
     then
    2.63
     or
    2.61
     would
    1.88
     that
    1.84
     say
    1.80
     immediately
    1.76
     they
    1.74
     Another
    1.73
     decât
    1.68
     has
    1.66
    Activations Density 0.094%

    No Known Activations