© 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. 22-GEMMASCOPE-RES-131K
    7. 70703
    Prev
    Next
    INDEX
    Explanations

    quantify, quantitative, quantification

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     zeal
    -1.03
    ✺
    -1.00
     Commissione
    -0.98
    eminent
    -0.98
     сообщение
    -0.96
    xbox
    -0.94
     읽
    -0.94
     исполь
    -0.94
     thai
    -0.93
    Berita
    -0.92
    POSITIVE LOGITS
     quantify
    1.25
     what
    1.20
     tangible
    1.09
    formal
    1.05
     mahdol
    1.00
     siitä
    0.93
    ”（
    0.93
    正式
    0.92
    onyme
    0.91
    itário
    0.91
    Activations Density 0.075%

    No Known Activations