© 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. 10989
    Prev
    Next
    INDEX
    Explanations

    code modules and libraries

    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
    ının
    -1.15
     schlafen
    -1.08
     schlaf
    -1.05
    ってみた
    -0.99
     Erinnerungen
    -0.98
     by
    -0.96
    𝒙
    -0.96
    namiento
    -0.96
    bracelet
    -0.96
    sweater
    -0.96
    POSITIVE LOGITS
     ennen
    1.13
     любого
    1.11
    Before
    1.05
     .”
    1.05
     delapan
    1.03
    expédition
    1.02
     weltweit
    1.02
    𝑄
    0.99
     voordat
    0.97
     definiciones
    0.97
    Activations Density 0.060%

    No Known Activations