© 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. 34545
    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
     pasas
    -1.38
     pulsa
    -1.36
     perna
    -1.36
     galeria
    -1.33
    鹀
    -1.32
     agreg
    -1.28
     sombr
    -1.27
     hunde
    -1.26
     gana
    -1.25
     negatif
    -1.24
    POSITIVE LOGITS
     H
    1.13
     \&
    1.13
     atractivos
    1.12
    b
    1.11
     \
    1.11
    ho
    1.06
    ]
    1.06
     maravillosas
    1.05
     объясня
    1.05
    u
    1.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.