© 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. 35444
    Prev
    Next
    INDEX
    Explanations

    corporate bonds

    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
     urethra
    0.46
     hun
    0.45
     Englishmen
    0.43
    ****",
    0.43
     każdego
    0.42
    ("|"+"
    0.42
    ***",
    0.42
     Μαρ
    0.41
    ServiceGroupID
    0.41
     Hendrik
    0.41
    POSITIVE LOGITS
    Kaz
    0.35
    \[
    0.35
    Lewis
    0.35
    ON
    0.34
    зов
    0.34
    Flood
    0.34
     現
    0.34
    Ŏ
    0.34
    Order
    0.33
    keley
    0.33
    Activations Density 0.000%

    No Known Activations