© 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. 111706
    Prev
    Next
    INDEX
    Explanations

    pleasure and pride

    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
     already
    -2.14
     about
    -1.99
     veranstal
    -1.90
     recently
    -1.69
     only
    -1.68
     where
    -1.64
     benutzt
    -1.61
     verknüp
    -1.60
     verändert
    -1.57
     giocatore
    -1.57
    POSITIVE LOGITS
     solides
    1.59
     etched
    1.48
     flotte
    1.40
     comedia
    1.39
     chimie
    1.36
     erken
    1.34
    ucks
    1.32
     fluide
    1.29
     yıl
    1.27
     nette
    1.27
    Activations Density 0.013%

    No Known Activations