© 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. 59598
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     läsa
    -1.39
     These
    -1.24
     in
    -1.18
     lära
    -1.15
     säga
    -1.13
    prüche
    -1.10
    责编
    -1.10
    僭
    -1.09
    苹
    -1.09
     FLUID
    -1.09
    POSITIVE LOGITS
     неболь
    1.22
     меры
    1.16
    ichert
    1.13
     nowy
    1.09
     \
    1.09
    急忙
    1.09
     новая
    1.02
    唔係
    1.01
     étaient
    1.01
    那
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.