© 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. 85728
    Prev
    Next
    INDEX
    Explanations

    specific nouns

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

    medical terms, diagnoses

    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
    vus
    0.48
     afirm
    0.47
     dizendo
    0.47
     exquisitely
    0.46
    蒂
    0.46
     формирования
    0.45
     వారి
    0.45
     तहे
    0.45
     ప్రజా
    0.45
     yǐ
    0.44
    POSITIVE LOGITS
    binary
    0.48
     binary
    0.47
    <b>
    0.43
     te
    0.43
    test
    0.42
     men
    0.42
    เฉพาะ
    0.41
    ทั้ง
    0.41
    ちなみに
    0.40
     bonded
    0.40
    Activations Density 0.001%

    No Known Activations