© 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. 186760
    Prev
    Next
    INDEX
    Explanations

    medical terminology and conditions

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

    ferryman, reporter, root, allow

    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
    Not in Any Lists

    No Comments

    Negative Logits
    emeinschaft
    0.55
    హిత
    0.51
    edin
    0.50
    єд
    0.50
    ప్తి
    0.48
    کز
    0.48
    ($"{
    0.48
    ן
    0.47
    들아
    0.46
     ኢ
    0.45
    POSITIVE LOGITS
     snowboard
    0.52
    让
    0.49
     abnormally
    0.49
    装
    0.48
     experience
    0.48
     to
    0.47
     injury
    0.46
    injury
    0.46
     use
    0.45
    ጀመሪያ
    0.45
    Activations Density 0.000%

    No Known Activations