© 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. 8249
    Prev
    Next
    INDEX
    Explanations

    White House officials and advisors

    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
     Kristus
    -1.36
     signifikan
    -1.30
     tragé
    -1.25
     berharap
    -1.24
     Karakter
    -1.22
     magnifique
    -1.21
    ⁾
    -1.19
    Ⅹ
    -1.18
     我们
    -1.17
    eafter
    -1.16
    POSITIVE LOGITS
     jednej
    1.20
    iyle
    1.15
    [
    1.09
     존
    1.06
     allein
    1.06
     воздей
    1.05
     run
    1.05
     neuen
    1.02
     аккумулятор
    1.02
     querer
    1.01
    Activations Density 0.048%

    No Known Activations