© 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-262K
    7. 1619
    Prev
    Next
    INDEX
    Explanations

    how to ask questions

    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_262k_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
    ↵
    0.30
     bar
    0.27
    া
    0.26
    0.24
     ganz
    0.23
     the
    0.23
     dese
    0.23
    /
    0.23
     with
    0.23
     Turing
    0.23
    POSITIVE LOGITS
     어떻게
    0.36
     succinctly
    0.34
     می‌تواند
    0.34
    สามารถ
    0.33
     কীভাবে
    0.33
     എങ്ങനെ
    0.33
    Should
    0.33
     должны
    0.32
     कशी
    0.32
     могло
    0.32
    Activations Density 0.031%

    No Known Activations