© 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. 124058
    Prev
    Next
    INDEX
    Explanations

    court or legal documents

    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
     to
    -2.77
    '
    -2.69
    とき
    -2.22
    
    -2.17
    型的
    -2.11
     oscu
    -2.09
    身的
    -2.09
     boun
    -2.09
    VIATIONS
    -2.03
    Ⓚ
    -2.02
    POSITIVE LOGITS
     να
    2.77
    to
    2.75
    泐
    2.73
    鵙
    2.45
     Anſ
    2.45
    n
    2.44
    獒
    2.41
    ();
    2.39
     Many
    2.38
    顚
    2.36
    Activations Density 0.001%

    No Known Activations