© 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. 34-GEMMASCOPE-RES-131K
    7. 23791
    Prev
    Next
    INDEX
    Explanations

    common sentence beginnings

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

    The neuron fires on numeric tokens (digit sequences), especially numbers embedded in code identifiers or version/license strings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Board
    -0.88
     board
    -0.86
    Board
    -0.78
    
    -0.71
     Wellen
    -0.71
     Purdy
    -0.68
     FTSE
    -0.67
     österreich
    -0.66
     eingesch
    -0.65
     Kabupaten
    -0.64
    POSITIVE LOGITS
    Camin
    0.90
     blender
    0.88
    DateTimeFormat
    0.82
     curry
    0.81
     фоль
    0.81
    tices
    0.81
     ko
    0.78
     exámenes
    0.77
     Cancun
    0.74
     Utilisez
    0.73
    Activations Density 0.007%

    No Known Activations