© 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. 10-GEMMASCOPE-RES-131K
    4. 47744
    Prev
    Next
    INDEX
    Explanations

    by increasing or improving

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

    The main thing this neuron does is detect numeric quantities and measurements (numbers and percentages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     that
    -1.89
     their
    -1.55
     this
    -1.39
     juos
    -1.34
    彼らは
    -1.33
     cierta
    -1.27
     ",";
    -1.27
    ふと
    -1.27
     =>
    
    -1.27
    beria
    -1.27
    POSITIVE LOGITS
     Verbraucher
    1.48
    jamientos
    1.47
     chances
    1.37
     мужа
    1.35
    чехол
    1.34
    heits
    1.34
    镲
    1.33
    自分が
    1.32
    で購入
    1.32
     специаль
    1.31
    Activations Density 0.160%

    No Known Activations