© 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. 41-GEMMASCOPE-2-RES-262K
    7. 7981
    Prev
    Next
    INDEX
    Explanations

    python code setup

    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_all/layer_41_width_262k_l0_big
    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
    <unused967>
    0.40
    ग्वि
    0.38
    াহরণ
    0.38
    ន្ថ
    0.38
     fragmentary
    0.37
    ব্লিউ
    0.36
    <unused153>
    0.36
    বিষ্য
    0.36
    ួក
    0.36
     constraining
    0.36
    POSITIVE LOGITS
    (
    0.43
     '
    0.36
      
    0.32
    [
    0.31
    1
    0.31
    n
    0.31
    /
    0.30
     p
    0.30
     Public
    0.30
    "
    0.30
    Activations Density 0.023%

    No Known Activations