© 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. 68541
    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
    👆
    -1.10
     beda
    -1.08
    ~•
    -1.06
     beker
    -1.05
     Amerik
    -1.05
     سپس
    -1.04
     Spanyol
    -1.04
     japon
    -1.04
     kado
    -1.03
    🔥🔥🔥
    -1.02
    POSITIVE LOGITS
     and
    1.09
     weist
    1.02
    asa
    0.99
     ведет
    0.98
     ,
    0.95
     powinna
    0.94
    ect
    0.94
     your
    0.91
    en
    0.90
    ith
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.