© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90263
    Prev
    Next
    INDEX
    Explanations

    buffer size limits

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

    This neuron detects numeric literals (numbers) in the 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
    Tien
    -0.96
    liziert
    -0.82
     faker
    -0.81
    outFile
    -0.79
     piaggio
    -0.79
    tangentMode
    -0.78
    cedures
    -0.78
     TIFF
    -0.77
     husqvarna
    -0.76
     jetta
    -0.75
    POSITIVE LOGITS
     MAX
    1.44
    MAX
    1.32
     maximum
    1.29
    max
    1.23
     max
    1.20
     maxLength
    1.18
     Max
    1.15
    Max
    1.14
     sizeof
    1.13
    maxLength
    1.13
    Activations Density 0.026%

    No Known Activations