© 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. 123999
    Prev
    Next
    INDEX
    Explanations

    icing, coating, frosting, sugar

    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
     hundred
    -1.68
    at
    -1.63
    2
    -1.62
    on
    -1.60
    3
    -1.52
      
    -1.51
    ence
    -1.48
    merkt
    -1.46
    so
    -1.45
    ",
    -1.45
    POSITIVE LOGITS
     Erfol
    1.55
     متحده
    1.52
    幛
    1.45
    してます
    1.44
     desierto
    1.40
     blatantly
    1.39
     steadfast
    1.38
     mammoth
    1.34
     valioso
    1.34
     pavimento
    1.34
    Activations Density 0.010%

    No Known Activations