© 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. 110931
    Prev
    Next
    INDEX
    Explanations

    sufficiency and quantity

    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
    「
    -1.77
    weitere
    -1.66
     parfü
    -1.63
    работки
    -1.61
     изображения
    -1.55
    还是
    -1.52
     piel
    -1.48
    ╽
    -1.48
    Więcej
    -1.48
    1
    -1.45
    POSITIVE LOGITS
    .”
    1.74
     evidenced
    1.73
    ’
    1.72
     zowel
    1.66
     hopes
    1.60
    无疑
    1.59
     journalistes
    1.48
     safeguards
    1.48
    in
    1.47
     allegedly
    1.45
    Activations Density 0.004%

    No Known Activations