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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37971
    Prev
    Next
    INDEX
    Explanations

    code object names

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

    The neuron is looking for programming identifiers—variable, type, and member names—in code snippets.

    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
    lacoste
    -0.96
    ього
    -0.91
     and
    -0.90
     already
    -0.88
     يحت
    -0.82
     setting
    -0.81
     maakt
    -0.80
    cosm
    -0.80
     setUp
    -0.80
     inside
    -0.80
    POSITIVE LOGITS
    try
    1.16
    BeginInit
    1.09
     Try
    1.05
    Try
    1.01
     ReSharper
    0.94
    ($"
    0.94
    [,]
    0.94
     pictureBox
    0.93
    ?).
    0.93
     as
    0.93
    Activations Density 0.015%

    No Known Activations