© 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. 10-GEMMASCOPE-RES-131K
    7. 68985
    Prev
    Next
    INDEX
    Explanations

    `interface` definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ”，
    -1.53
    
    -1.48
    }}
    -1.45
    ))
    -1.44
    ”？
    -1.38
     is
    -1.38
     certainly
    -1.29
     it
    -1.27
    sy
    -1.26
     использовать
    -1.26
    POSITIVE LOGITS
    racked
    1.73
     gevolg
    1.64
     resultaat
    1.62
     gebouw
    1.54
    owników
    1.53
    不
    1.51
    licante
    1.49
     duque
    1.48
     feine
    1.47
     notables
    1.43
    Activations Density 0.148%

    No Known Activations