© 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. 131587
    Prev
    Next
    INDEX
    Explanations

    command line syntax and variables

    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
     eggplant
    0.58
     aub
    0.47
     passphrase
    0.45
     dest
    0.44
     Aub
    0.42
     Dest
    0.41
     ◆
    0.41
     emin
    0.41
    ătă
    0.41
     lines
    0.40
    POSITIVE LOGITS
     ${
    1.07
    ${
    1.03
     ¹
    0.98
     "${
    0.94
     '${
    0.90
    }${
    0.88
    :${
    0.87
     `${
    0.86
    =${
    0.86
    ">${
    0.86
    Activations Density 0.017%

    No Known Activations