© 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. 256165
    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
     стандарта
    0.53
    ін
    0.52
    𒄀
    0.51
    できる
    0.50
     ಅವನ
    0.50
    лез
    0.48
    ۳
    0.48
    鍍
    0.48
    竪
    0.48
    کہ
    0.47
    POSITIVE LOGITS
    Reading
    0.47
     Qu
    0.44
     Pember
    0.44
    Neighbors
    0.43
     Ig
    0.42
     N
    0.42
     Reading
    0.42
     Balance
    0.41
    League
    0.41
    Control
    0.40
    Activations Density 0.001%

    No Known Activations