© 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. 44547
    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
     and
    -1.45
     Hivatalos
    -1.23
     to
    -1.19
     Widers
    -1.05
     amizade
    -1.05
     I
    -1.02
     Their
    -1.00
     All
    -0.97
    開心
    -0.96
     we
    -0.96
    POSITIVE LOGITS
    tronlink
    1.27
     UNIVER
    1.23
     rafael
    1.23
     BASKET
    1.23
     fernando
    1.22
     terapi
    1.22
     terap
    1.19
    wheres
    1.19
     roberto
    1.17
    bestimmung
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.