© 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. 75983
    Prev
    Next
    INDEX
    Explanations

    microcontroller and STM32 variants

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

    The neuron strongly activates on numeric tokens (e.g. version numbers, register values, model numbers) in code comments and identifiers.

    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
    decoded
    -0.87
    囯
    -0.81
     domin
    -0.75
     holes
    -0.74
     Weed
    -0.74
    GARD
    -0.73
     weed
    -0.73
    插件
    -0.71
     jardin
    -0.70
    phis
    -0.70
    POSITIVE LOGITS
     Cortex
    0.97
     MCU
    0.97
     stm
    0.81
     STM
    0.76
     microcontroller
    0.76
     uf
    0.75
    الحي
    0.73
    ulos
    0.72
     AES
    0.70
     entraîne
    0.70
    Activations Density 0.066%

    No Known Activations