© 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. 66177
    Prev
    Next
    INDEX
    Explanations

    Trinidadian, trade winds, Triboa

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

    The neuron activates on numeric tokens—numbers, measurements, years, and other digit sequences 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
     grasas
    -0.74
     pitch
    -0.72
    video
    -0.70
     кру
    -0.70
     said
    -0.69
     loaded
    -0.68
     Staats
    -0.68
     cont
    -0.65
    simon
    -0.65
     black
    -0.65
    POSITIVE LOGITS
    TRADE
    0.92
    nitzel
    0.79
    Trades
    0.78
     eenen
    0.77
     dziewczyn
    0.75
     Sear
    0.75
     TRADE
    0.74
    ㅚ
    0.74
    enchymal
    0.74
     mowing
    0.73
    Activations Density 0.020%

    No Known Activations