© 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. 11098
    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
     will
    -1.45
          
    -1.29
    </b>
    -1.19
    ',
    -1.13
    ↵
    -1.13
    i
    -1.08
    

    -1.05
     is
    -1.03
    "
    -1.01
     m
    -1.00
    POSITIVE LOGITS
    
    1.16
     especta
    1.16
     戦士
    1.14
    睒
    1.14
    سرائ
    1.13
    ⇴
    1.07
     祭り
    1.05
     dessins
    1.03
     albeit
    1.03
     représ
    1.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.