© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27212
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     silikon
    -1.31
     mikrofon
    -1.24
     ekos
    -1.23
     triko
    -1.21
    bagian
    -1.20
     alkoh
    -1.20
     stadion
    -1.19
     höl
    -1.17
     ekolog
    -1.16
     katalog
    -1.15
    POSITIVE LOGITS
     re
    1.09
     with
    1.09
     has
    1.05
     öfter
    1.01
     anpassen
    1.00
     g
    0.99
     Sh
    0.98
     ultra
    0.97
     angefü
    0.96
     f
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.