© 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. 3300
    Prev
    Next
    INDEX
    Explanations

    enterprise software and projects

    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
     lmao
    0.50
    心中的
    0.47
     Patreon
    0.47
     pygame
    0.45
     chu
    0.45
     libertarian
    0.45
    npy
    0.45
     ܐ
    0.44
     idk
    0.44
    ọc
    0.44
    POSITIVE LOGITS
     SAP
    1.19
     Oracle
    1.13
    SAP
    1.07
    Oracle
    1.06
     mainframe
    0.93
     ServiceNow
    0.92
     Talend
    0.83
     IBM
    0.81
     Citrix
    0.80
     SQL
    0.80
    Activations Density 0.523%

    No Known Activations