© 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. 11923
    Prev
    Next
    INDEX
    Explanations

    unit of measurement

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

    The neuron fires on numeric tokens or numeric sequences (e.g. numbers, codes, or numeric measurements) in the 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
    numericUpDown
    -0.83
     міні
    -0.82
     trabalhar
    -0.81
     budete
    -0.78
     conhecido
    -0.77
     чор
    -0.77
     Espíritu
    -0.75
     працю
    -0.74
     located
    -0.74
    overall
    -0.73
    POSITIVE LOGITS
     unit
    0.91
     equal
    0.91
    昔
    0.89
     définition
    0.88
     internationale
    0.86
     gancho
    0.86
     definition
    0.84
     international
    0.84
    悔
    0.83
     Derived
    0.83
    Activations Density 0.013%

    No Known Activations