© 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. 213285
    Prev
    Next
    INDEX
    Explanations

    dental and medical professionals

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

    objective values

    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
     り
    0.52
     토
    0.49
     જય
    0.48
     пе
    0.47
    inata
    0.47
     เฟ
    0.47
     Dred
    0.46
     드리
    0.46
     पे
    0.45
     動画
    0.45
    POSITIVE LOGITS
    ى
    0.64
    ية
    0.53
    مة
    0.52
    نة
    0.50
    ة
    0.49
    كمة
    0.48
    لاة
    0.46
     inflamm
    0.46
    تميز
    0.46
    كر
    0.45
    Activations Density 0.001%

    No Known Activations