© 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. 79640
    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
    elsif
    -1.24
     intér
    -1.15
     }],
    -1.13
     more
    -1.09
     it
    -1.05
    appBar
    -1.03
    øg
    -1.03
     soyez
    -1.02
     trying
    -1.01
     />}
    -1.01
    POSITIVE LOGITS
    了些
    1.42
    了许多
    1.26
    кзак
    1.23
    了不少
    1.20
    了什么
    1.16
    RESUMEN
    1.16
     dasselbe
    1.15
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.14
     momentous
    1.14
    がたくさん
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.