© 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. 79794
    Prev
    Next
    INDEX
    Explanations

    Q followed by UNITED

    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_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
     ?
    -1.11
     vuitton
    -1.08
    或是
    -0.98
     acept
    -0.96
     constituents
    -0.94
    !
    -0.92
     fritas
    -0.90
    。『
    -0.90
     kronor
    -0.90
    优雅
    -0.90
    POSITIVE LOGITS
    siamo
    1.20
    かもしれませんが
    1.06
    
    1.03
    夊
    1.03
    changers
    1.02
     Autre
    1.02
     território
    1.02
    adventures
    1.01
    Chiara
    0.99
     vė
    0.98
    Activations Density 0.000%

    No Known Activations