© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1954
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inny
    0.20
     đây
    0.18
     invertible
    0.18
    0.17
     等
    0.17
     ၁
    0.17
     юк
    0.17
     "*"
    0.17
     ikki
    0.17
     kaha
    0.16
    POSITIVE LOGITS
     ultimately
    0.38
     subsequently
    0.36
     zároveň
    0.34
     provide
    0.34
     hopefully
    0.30
     ensure
    0.29
     thereby
    0.29
     consequently
    0.29
     also
    0.28
    provide
    0.27
    Activations Density 1.142%

    No Known Activations