© 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. 48451
    Prev
    Next
    INDEX
    Explanations

    variable declarations

    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
    ]<<"
    -1.45
    $("
    -1.45
     Öffnen
    -1.41
    「
    -1.39
     śmierci
    -1.38
     tienden
    -1.38
    เพราะ
    -1.38
     forskning
    -1.37
    
    -1.36
     เพราะ
    -1.35
    POSITIVE LOGITS
     are
    2.33
     also
    2.13
     will
    1.81
     também
    1.70
     should
    1.70
     can
    1.59
     тоже
    1.47
     cannot
    1.44
     This
    1.40
     также
    1.40
    Activations Density 0.013%

    No Known Activations