© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11153
    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
     their
    -1.32
     Schule
    -1.28
     Dezember
    -1.20
     love
    -1.16
    래스
    -1.13
     best
    -1.13
    攷
    -1.10
     only
    -1.09
     her
    -1.09
     plaît
    -1.06
    POSITIVE LOGITS
     DEFEND
    1.33
    yden
    1.27
     essenziale
    1.25
     endgül
    1.23
     protezione
    1.21
     ویت
    1.19
    샅
    1.19
     이미
    1.19
     могли
    1.18
    Produkte
    1.18
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.