© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 257939
    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
    я
    0.52
     খোলা
    0.48
    Stanley
    0.48
    AC
    0.46
    Obama
    0.46
            
    0.46
    Rio
    0.45
    Ю
    0.45
    Kerry
    0.44
    PC
    0.44
    POSITIVE LOGITS
     UIKit
    0.51
    𝕟
    0.46
    mushroom
    0.44
     kN
    0.44
    seem
    0.43
    kN
    0.43
    릉
    0.43
     Lä
    0.43
     Krakow
    0.42
    alena
    0.42
    Activations Density 0.001%

    No Known Activations