© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14092
    Prev
    Next
    INDEX
    Explanations

    class names and components

    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
     différents
    -1.60
    marché
    -1.53
     diseñadores
    -1.50
    饜
    -1.50
    
    -1.48
    
    -1.42
    despite
    -1.42
     variados
    -1.41
     micrófono
    -1.39
     poë
    -1.38
    POSITIVE LOGITS
     on
    1.85
     with
    1.65
     having
    1.47
     because
    1.44
     regarding
    1.41
     providing
    1.40
    Because
    1.34
     out
    1.32
     had
    1.32
    openConnection
    1.30
    Activations Density 0.052%

    No Known Activations