© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 255029
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Exchequer
    0.54
     Віль
    0.50
     Medici
    0.49
     Victim
    0.48
    府
    0.48
     UserRepository
    0.47
    حان
    0.46
     Irrigation
    0.46
     Arthritis
    0.46
     Controller
    0.46
    POSITIVE LOGITS
    salary
    0.49
    抛
    0.48
     ți
    0.47
    OC
    0.46
    净
    0.45
     classmate
    0.44
    complete
    0.44
    sigma
    0.44
    ங்களால்
    0.44
     spark
    0.44
    Activations Density 0.001%

    No Known Activations