© 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. 129831
    Prev
    Next
    INDEX
    Explanations

    academic institutions and organizations

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

    coach abusing

    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
    s
    0.55
     Tipo
    0.49
     ebenfalls
    0.48
    t
    0.48
     stejně
    0.47
     bohater
    0.46
     Blut
    0.46
    a
    0.45
     Style
    0.45
     pairing
    0.45
    POSITIVE LOGITS
     বিশ্ববিদ্যাল
    0.50
     professors
    0.46
     उद्यम
    0.46
     বিশ্ববিদ্যালয়ে
    0.46
     institution
    0.45
     Faculties
    0.45
     boroughs
    0.45
    學生
    0.45
     universities
    0.45
     institutions
    0.45
    Activations Density 0.002%

    No Known Activations