© 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. 22-GEMMASCOPE-RES-131K
    7. 26241
    Prev
    Next
    INDEX
    Explanations

    Latin roots and endings

    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
    L
    -1.09
    R
    -1.09
    N
    -1.01
    H
    -1.00
    G
    -0.99
    T
    -0.98
     reduced
    -0.95
    E
    -0.95
     things
    -0.95
    二つ
    -0.94
    POSITIVE LOGITS
    棪
    1.05
    桡
    1.02
     bú
    1.01
     Correo
    0.99
    キュリティ
    0.98
     disponibilités
    0.98
     consé
    0.98
    柑
    0.96
    IQR
    0.96
     mó
    0.95
    Activations Density 0.006%

    No Known Activations