© 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. 73706
    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
     from
    -1.57
     if
    -1.36
     daca
    -1.27
    
    -1.20
     ujar
    -1.20
     Gemeinsame
    -1.18
     for
    -1.16
    넋
    -1.16
     senin
    -1.16
     If
    -1.16
    POSITIVE LOGITS
    ↵↵
    1.49
    )
    1.08
    C
    1.05
     focuses
    1.03
     bedingt
    1.02
    J
    1.00
     Funktionalität
    1.00
     oxígeno
    0.98
    actually
    0.98
     Ausgaben
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.