© 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. 185658
    Prev
    Next
    INDEX
    Explanations

    medical and legal contexts

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

    medical advice, understanding BLW

    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
     okaz
    0.50
    캇
    0.49
     Descartes
    0.48
     succession
    0.47
     possessions
    0.47
     הב
    0.46
     ይቀ
    0.46
     유지
    0.46
     ခ
    0.46
     Entrenamiento
    0.45
    POSITIVE LOGITS
    ار
    0.67
    ar
    0.58
    ic
    0.55
    شهاد
    0.53
    ند
    0.52
    ست
    0.52
    ed
    0.51
    ضر
    0.50
    ous
    0.49
    噸
    0.49
    Activations Density 0.000%

    No Known Activations