© 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. 12981
    Prev
    Next
    INDEX
    Explanations

    Category names

    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
     calendriers
    -1.54
     炖
    -1.44
     elektronik
    -1.41
    馊
    -1.41
     ſal
    -1.40
     lez
    -1.40
     oublier
    -1.39
    tengo
    -1.38
     花朵
    -1.36
     実例
    -1.35
    POSITIVE LOGITS
     T
    1.70
     S
    1.64
     L
    1.55
     of
    1.55
     M
    1.53
    L
    1.52
     D
    1.50
     t
    1.44
     h
    1.43
     re
    1.43
    Activations Density 0.039%

    No Known Activations