© 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. 109311
    Prev
    Next
    INDEX
    Explanations

    structure initialization

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

    This neuron detects numeric tokens (digits, numbers, and numeric literals) 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_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
     welches
    -0.94
     которое
    -0.94
     stesso
    -0.88
     its
    -0.88
     első
    -0.83
     Gnade
    -0.81
     toate
    -0.80
    cythe
    -0.79
     himself
    -0.77
     itself
    -0.77
    POSITIVE LOGITS
     herself
    1.21
    ={
    1.02
    herself
    0.93
    memset
    0.91
    struct
    0.90
    née
    0.88
    {.
    0.88
    յ
    0.88
    atissimo
    0.88
     voorbeeld
    0.86
    Activations Density 0.016%

    No Known Activations