© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129848
    Prev
    Next
    INDEX
    Explanations

    privilege and special status

    np_acts-logits-general · gemini-2.5-flash-lite

    events and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Schatten
    0.53
     Плавание
    0.45
     Undert
    0.44
    阴
    0.43
     Likewise
    0.42
    Miguel
    0.42
    ToDo
    0.42
    더
    0.42
     Miguel
    0.41
    Alternatively
    0.41
    POSITIVE LOGITS
     multiplic
    0.46
    প্রবাসী
    0.46
     ውጤ
    0.45
     thermally
    0.45
     différen
    0.45
     privileged
    0.45
     privil
    0.45
     cordon
    0.44
     worrisome
    0.44
     privileges
    0.42
    Activations Density 0.000%

    No Known Activations