© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116129
    Prev
    Next
    INDEX
    Explanations

    scatter plot diagrams

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

    The neuron activates on numeric tokens—numbers or sequences of digits 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
    sé
    -0.72
     zehn
    -0.72
    istisch
    -0.71
    brett
    -0.70
    Song
    -0.69
    Algorithms
    -0.69
     seated
    -0.68
    Seat
    -0.68
     пы
    -0.67
     Sitz
    -0.67
    POSITIVE LOGITS
     plot
    1.91
     diagram
    1.85
     plots
    1.59
     scatter
    1.57
     diagrams
    1.52
     Diagram
    1.37
    diagram
    1.30
    scatter
    1.26
    plot
    1.21
     diagrama
    1.16
    Activations Density 0.039%

    No Known Activations