© 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. 22-GEMMASCOPE-RES-131K
    4. 93312
    Prev
    Next
    INDEX
    Explanations

    units of measurement and quantities

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

    The neuron selectively activates on numeric measurement values—especially decimals—often paired with units.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     inexpensive
    -0.98
     AnyObject
    -0.96
     muhimu
    -0.90
     elettrico
    -0.89
    LogFile
    -0.89
     geschaffen
    -0.87
     itemView
    -0.87
     vuol
    -0.87
    ようになった
    -0.86
    printStackTrace
    -0.86
    POSITIVE LOGITS
     including
    1.38
     включая
    1.34
     plus
    1.32
    本体
    1.23
     overall
    1.23
     основ
    1.16
    including
    1.14
    Including
    1.13
     плюс
    1.10
     with
    1.07
    Activations Density 0.056%

    No Known Activations