© 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. 4037
    Prev
    Next
    INDEX
    Explanations

    pd

    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
    䞍
    0.47
    durationType
    0.45
    uyeron
    0.45
    physiological
    0.45
    옻
    0.45
     encryption
    0.45
     азо
    0.45
    encryption
    0.44
    enumi
    0.44
     minSdkVersion
    0.44
    POSITIVE LOGITS
     pandas
    2.45
     Pandas
    2.45
    pandas
    2.17
     panda
    2.16
     Panda
    2.08
    panda
    1.84
    Pand
    1.84
    熊猫
    1.71
     pd
    1.69
    🐼
    1.69
    Activations Density 0.009%

    No Known Activations