© 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. 32156
    Prev
    Next
    INDEX
    Explanations

    using NuGet packages

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

    This neuron fires on uppercase technical identifiers and keywords (e.g. build‐script or project‐configuration tokens) in code or XML.

    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
    pygame
    -1.08
    handleClose
    -0.79
    ]))
    -0.77
    btnClose
    -0.77
    olí
    -0.73
    JPanel
    -0.73
    مص
    -0.72
     interpretar
    -0.71
    hollywood
    -0.70
    orianCalendar
    -0.69
    POSITIVE LOGITS
     Visual
    1.39
     VS
    1.18
    Visual
    1.13
     ReSharper
    1.09
     solution
    1.05
     deven
    1.02
     nugget
    0.95
    visual
    0.93
     IIS
    0.91
    Nu
    0.89
    Activations Density 0.335%

    No Known Activations