© 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. 149876
    Prev
    Next
    INDEX
    Explanations

    extended interfaces

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

    states of being or parts

    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
     Lettuce
    0.45
     здравоохранения
    0.45
     कार्यक्रमों
    0.43
     programas
    0.41
     Populations
    0.41
     Programs
    0.40
     Organizations
    0.40
     PROGRAMS
    0.40
     프로그램을
    0.40
    孵
    0.40
    POSITIVE LOGITS
    েষে
    0.62
     reissue
    0.49
     retomar
    0.46
    ulong
    0.46
     foolish
    0.46
     resolv
    0.46
     ritor
    0.45
     revenir
    0.44
     tiring
    0.44
     menjelaskan
    0.44
    Activations Density 0.001%

    No Known Activations