© 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. 99968
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming

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

    The neuron strongly activates on numeric literals (sequences of digits) 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
     mentre
    -0.91
     berech
    -0.86
    ()}}
    -0.85
    fillType
    -0.84
    akteur
    -0.82
     ejercer
    -0.82
     Don
    -0.81
    scriptId
    -0.79
     boî
    -0.79
    kå
    -0.78
    POSITIVE LOGITS
    .《
    0.98
    Kristina
    0.94
    喁
    0.90
     storici
    0.88
     Toscana
    0.88
    极了
    0.87
    Père
    0.87
     touché
    0.87
     сада
    0.85
    Helmut
    0.85
    Activations Density 0.020%

    No Known Activations