© 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. 100602
    Prev
    Next
    INDEX
    Explanations

    immediately before or after an event

    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
    .
    -1.55
     untold
    -1.41
     cute
    -1.41
     T
    -1.41
     mere
    -1.40
     rant
    -1.40
     
    -1.39
     Перейти
    -1.39
     siendo
    -1.38
     Erkennt
    -1.37
    POSITIVE LOGITS
     küche
    1.80
    哢
    1.77
     sortes
    1.73
     ingrédients
    1.72
     zelve
    1.70
    蚍
    1.66
     oreilles
    1.66
     médec
    1.61
     本店
    1.59
    posisi
    1.55
    Activations Density 0.020%

    No Known Activations