© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40145
    Prev
    Next
    INDEX
    Explanations

    UI components and layout elements

    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
    饜
    -1.52
     Hentet
    -1.50
    鴆
    -1.48
    曾經
    -1.43
     why
    -1.37
    obut
    -1.35
     cwt
    -1.34
     presi
    -1.30
    citement
    -1.30
    ortic
    -1.29
    POSITIVE LOGITS
    merkungen
    1.49
    '
    1.45
    Banyak
    1.43
     us
    1.40
    setObjectName
    1.33
    重要的是
    1.30
    Informasi
    1.30
     
    1.30
    孕妇
    1.28
     Ön
    1.27
    Activations Density 0.005%

    No Known Activations