© 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. 108795
    Prev
    Next
    INDEX
    Explanations

    inquiries and relationships

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

    medical information for simplicity

    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
    νον
    0.54
    ंति
    0.45
     witnessing
    0.43
    rikan
    0.43
    ̆
    0.42
    iki
    0.42
    రి
    0.41
    櫛
    0.41
    (',',
    0.40
    czeń
    0.40
    POSITIVE LOGITS
     Arsenal
    0.47
     सात
    0.46
    晚餐
    0.43
     کوتاه
    0.43
     сигнал
    0.42
     هولندا
    0.42
     आसानी
    0.41
     그냥
    0.41
     인해
    0.41
    Arsenal
    0.41
    Activations Density 0.000%

    No Known Activations