© 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. 57570
    Prev
    Next
    INDEX
    Explanations

    SQL query and schema definitions

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

    The neuron strongly activates on standalone numeric literals (integer constants) in code.

    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
     drastic
    -1.12
     substantial
    -1.02
     sparked
    -1.02
     nearing
    -1.02
     heightened
    -0.98
     spurred
    -0.97
     two
    -0.97
     regarding
    -0.97
     dozens
    -0.94
     large
    -0.93
    POSITIVE LOGITS
    designed
    0.91
     WOOD
    0.90
    stype
    0.88
    Orders
    0.87
     ordres
    0.86
     ICollection
    0.85
    nte
    0.85
     reseña
    0.84
    peed
    0.84
    often
    0.83
    Activations Density 0.010%

    No Known Activations