© 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. 124006
    Prev
    Next
    INDEX
    Explanations

    Eva Longoria, Western Buddhism, Q:

    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
     régal
    -1.76
     rése
    -1.70
     rév
    -1.66
     épu
    -1.62
    艫
    -1.60
    sisting
    -1.59
    姈
    -1.57
     réjou
    -1.56
    though
    -1.55
     mû
    -1.55
    POSITIVE LOGITS
     would
    2.11
     not
    1.68
    ритори
    1.63
     But
    1.49
     celebrating
    1.48
    시간
    1.48
     could
    1.45
     their
    1.43
     sarebbe
    1.41
    étaient
    1.41
    Activations Density 0.008%

    No Known Activations