© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41226
    Prev
    Next
    INDEX
    Explanations

    Stokes, marathon, race, Prep School, Broadway

    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
     has
    -1.55
     eliminates
    -1.48
     does
    -1.45
     is
    -1.44
    楽しみです
    -1.43
     reduced
    -1.41
     expands
    -1.41
    补贴
    -1.40
     creates
    -1.39
     defines
    -1.38
    POSITIVE LOGITS
    “
    1.45
    ,
    1.42
    走
    1.39
     توضی
    1.39
    wertig
    1.39
    綃
    1.38
    苼
    1.38
    wochen
    1.36
     plufieurs
    1.34
    öffnung
    1.32
    Activations Density 0.189%

    No Known Activations