© 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. 207924
    Prev
    Next
    INDEX
    Explanations

    medical terms and diagnoses

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

    Development Program

    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
    sal
    0.54
    YAN
    0.51
    saan
    0.49
    Rp
    0.48
     스타일
    0.46
    ႃႇ
    0.46
    н
    0.46
    a
    0.45
     salido
    0.45
    sah
    0.45
    POSITIVE LOGITS
     Teor
    0.50
     Polish
    0.49
     Luftwaffe
    0.45
     progn
    0.45
     Noct
    0.45
     thống
    0.44
     threatening
    0.44
     Obstetrics
    0.44
     Threat
    0.43
     Knoll
    0.43
    Activations Density 0.001%

    No Known Activations