© 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. 13389
    Prev
    Next
    INDEX
    Explanations

    instructions or notes

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

    The main thing this neuron does is detect numerical tokens (digits, quantities, and 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_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
    yoruz
    -1.05
    нием
    -1.03
     Поэтому
    -1.02
     منذ
    -1.01
     plutôt
    -0.99
    ventilador
    -0.98
     Derfor
    -0.97
     которых
    -0.96
     الأولى
    -0.94
    まずは
    -0.94
    POSITIVE LOGITS
     if
    1.62
     thereafter
    1.28
     Alternatively
    1.27
    完成です
    1.17
     afterwards
    1.15
     если
    1.13
    Alternatively
    1.07
     apabila
    1.06
     afterward
    1.05
    Noten
    1.05
    Activations Density 0.008%

    No Known Activations