© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 498
    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_16_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
    자
    1.39
    dır
    1.30
    ção
    1.18
    ع
    1.16
    л
    1.16
    지만
    1.15
    ς
    1.12
    ক
    1.09
    簹
    1.09
    ح
    1.09
    POSITIVE LOGITS
    am
    1.21
    n
    1.20
    in
    1.02
     sanit
    1.00
     instal
    0.99
    ν
    0.97
     legitim
    0.97
    urbation
    0.96
     decid
    0.93
    inink
    0.91
    Activations Density 2.996%

    No Known Activations