© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 3587
    Prev
    Next
    INDEX
    Explanations

    experimental design and testing

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    硖
    0.50
    ArchivePath
    0.45
    遄
    0.44
     Mathematica
    0.44
    缟
    0.44
     Printing
    0.43
    lmfit
    0.43
    侔
    0.43
    SubDirectoryPath
    0.42
     Pent
    0.42
    POSITIVE LOGITS
    投放
    0.66
     personalization
    0.60
     serving
    0.59
     campaigns
    0.58
    serving
    0.57
    feature
    0.56
     campañas
    0.56
    召
    0.56
     ऑफलाइन
    0.55
     fraud
    0.55
    Activations Density 0.155%

    No Known Activations