© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129396
    Prev
    Next
    INDEX
    Explanations

    Infernal Affairs

    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
    
    -2.98
    萏
    -2.80
    
    -2.50
    葙
    -2.42
    ጺ
    -2.42
    ୬
    -2.41
    蛩
    -2.39
    ους
    -2.34
    vertible
    -2.31
    Czytaj
    -2.31
    POSITIVE LOGITS
     we
    2.98
     –
    2.73
    ’
    2.56
    ;
    2.42
    ve
    2.31
    …’
    2.30
    .’
    2.27
     he
    2.20
    ’,
    2.14
    ,”
    2.13
    Activations Density 0.027%

    No Known Activations