© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9951
    Prev
    Next
    INDEX
    Explanations

    blender, processors, typewriter, machine

    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
    “:
    -1.48
     eingeführt
    -1.43
     preferências
    -1.41
    為に
    -1.39
    télé
    -1.39
    petits
    -1.38
    RoomId
    -1.37
    ,“
    -1.37
     praktijk
    -1.32
    离开
    -1.30
    POSITIVE LOGITS
    攪
    1.62
     jakość
    1.48
     млрд
    1.48
     >
    1.39
    苳
    1.38
     How
    1.37
     them
    1.36
     нам
    1.34
    ляет
    1.30
     doesnt
    1.30
    Activations Density 0.012%

    No Known Activations