© 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. 90529
    Prev
    Next
    INDEX
    Explanations

    numbers and digits

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

    The neuron is picking up numeric tokens—individual digits and numbers (e.g. lengths, parameter values, constants) in code or technical text.

    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
     tū
    -0.81
     TimeUnit
    -0.78
    ース
    -0.78
     alojamientos
    -0.75
    rijfs
    -0.74
    ﺎ
    -0.73
    の名
    -0.72
    λες
    -0.72
     virtue
    -0.69
     灵
    -0.69
    POSITIVE LOGITS
     eight
    1.63
     six
    1.46
     seven
    1.37
     nine
    1.36
     twelve
    1.34
     sixteen
    1.30
    eight
    1.20
     zwölf
    1.16
     fourteen
    1.10
     eleven
    1.09
    Activations Density 0.059%

    No Known Activations