© 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. 33323
    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
     has
    -1.47
     would
    -1.30
     does
    -1.25
     seems
    -1.22
     it
    -1.22
     provide
    -1.21
     provides
    -1.17
     began
    -1.16
     usually
    -1.15
     took
    -1.13
    POSITIVE LOGITS
    苙
    1.11
    Compte
    1.09
    躄
    1.08
    forcing
    1.03
     trám
    1.03
     trabajador
    1.00
    えもん
    0.98
    agence
    0.98
    conducted
    0.98
     toutefois
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.