© 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. 23929
    Prev
    Next
    INDEX
    Explanations

    cell therapy to data migration

    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
     its
    -1.40
    蛧
    -1.30
    ogues
    -1.28
    ING
    -1.27
    шень
    -1.26
     on
    -1.23
     используя
    -1.23
    si
    -1.23
    dings
    -1.21
    test
    -1.19
    POSITIVE LOGITS
     that
    1.70
     Vergnügen
    1.49
     maceta
    1.45
     manguera
    1.44
     okno
    1.44
     cielos
    1.41
     olej
    1.41
     blauen
    1.34
     opportunity
    1.34
     sartén
    1.33
    Activations Density 0.012%

    No Known Activations