© 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. 70846
    Prev
    Next
    INDEX
    Explanations

    iOS UI elements and libraries

    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
     one
    -1.63
     two
    -1.63
    }
    -1.57
     незавер
    -1.56
     noticeably
    -1.44
    },
    -1.42
     chose
    -1.42
     would
    -1.39
     Allgemeinen
    -1.31
    Bees
    -1.31
    POSITIVE LOGITS
     élégante
    1.50
    
    1.48
    formerly
    1.45
     doloroso
    1.42
     Vám
    1.38
     desperdic
    1.36
    幽默
    1.34
    ㉗
    1.34
    logiques
    1.34
     engraçado
    1.34
    Activations Density 0.005%

    No Known Activations