© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63857
    Prev
    Next
    INDEX
    Explanations

    anniversary gifts, laser printers, online orders

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

    This neuron fires on technical keywords and commands for querying or displaying data—particularly terms associated with business‐intelligence tools (e.g. QlikView’s display/data commands and “set analysis”).

    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
     filters
    -0.79
    杞
    -0.75
    缈
    -0.69
    ilstein
    -0.69
    的数量
    -0.67
    mT
    -0.66
    wiada
    -0.65
     interviewed
    -0.65
     subscribers
    -0.64
     queried
    -0.64
    POSITIVE LOGITS
     Wilkes
    0.84
     associ
    0.79
    QV
    0.78
     trion
    0.77
     straight
    0.77
     fever
    0.76
    chairs
    0.76
    bim
    0.75
     ASSOCI
    0.74
     Straight
    0.74
    Activations Density 0.017%

    No Known Activations