© 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. 32428
    Prev
    Next
    INDEX
    Explanations

    product identification standards

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

    The neuron predominantly activates on standalone numeric tokens or multi‐digit sequences (i.e., numbers).

    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
     customerId
    -0.75
     gunpowder
    -0.74
     comboBox
    -0.73
     Rockland
    -0.73
     VBox
    -0.72
    一覧
    -0.71
    ropolis
    -0.71
    ⠀⠀⠀⠀⠀⠀⠀⠀
    -0.71
     AKP
    -0.70
     TCR
    -0.68
    POSITIVE LOGITS
     GS
    1.55
    GS
    1.12
     gs
    0.96
     Retail
    0.87
     retail
    0.83
     Auto
    0.81
    яти
    0.79
    UDI
    0.79
    Retail
    0.77
     EPC
    0.77
    Activations Density 0.033%

    No Known Activations