© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13055
    Prev
    Next
    INDEX
    Explanations

    queen and titles

    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
     üblichen
    -2.42
     amerikanischen
    -2.33
     erwähnten
    -2.28
     berühmten
    -2.25
     gewünschten
    -2.22
     offiziellen
    -2.19
     betreffenden
    -2.19
     bekannten
    -2.17
     ehemaligen
    -2.16
     neuesten
    -2.11
    POSITIVE LOGITS
    ’，
    2.33
     famili
    2.16
     ilumina
    2.09
     хотела
    2.02
     of
    2.02
     Obr
    2.00
    骜
    2.00
    
    1.95
     ROUTE
    1.94
    蟊
    1.92
    Activations Density 0.010%

    No Known Activations