© 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. 10-GEMMASCOPE-RES-131K
    7. 70582
    Prev
    Next
    INDEX
    Explanations

    mathematical questions

    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_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
     uyt
    -2.03
     москве
    -1.89
    鼍
    -1.85
     régal
    -1.80
     februari
    -1.77
    کہ
    -1.73
     that
    -1.70
    縠
    -1.69
    besondere
    -1.67
    蚰
    -1.66
    POSITIVE LOGITS
     
    2.20
     still
    2.02
     has
    1.85
     there
    1.71
     will
    1.60
     can
    1.57
     kept
    1.57
     made
    1.55
     slated
    1.52
    ↵
    1.51
    Activations Density 0.176%

    No Known Activations