© 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. 29087
    Prev
    Next
    INDEX
    Explanations

    words followed by specific tokens

    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
    le
    -2.22
    .
    -2.19
    as
    -2.03
    s
    -2.00
    ki
    -1.99
    ,’
    -1.87
    瘫
    -1.84
     некоторы
    -1.80
    ON
    -1.80
    ve
    -1.80
    POSITIVE LOGITS
     '
    2.42
    .''
    2.22
    ↵
    2.20
     of
    2.03
    煳
    1.98
    滹
    1.90
    
    1.90
     ditemui
    1.89
     rappelle
    1.88
     appelé
    1.87
    Activations Density 0.001%

    No Known Activations