© 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. 16-GEMMASCOPE-2-RES-16K
    7. 768
    Prev
    Next
    INDEX
    Explanations

    As sentence start

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

    starts with ## or "

    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_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    k
    0.47
    il
    0.41
    ts
    0.41
    ises
    0.39
    ous
    0.38
    ine
    0.38
    ip
    0.38
    ants
    0.37
    ation
    0.36
    ítés
    0.36
    POSITIVE LOGITS
    इंडीज
    0.34
     tzv
    0.34
    হ
    0.33
     Chowdh
    0.33
    τ
    0.33
     comenz
    0.32
    ంద్ర
    0.32
     lanz
    0.32
    σε
    0.32
     cual
    0.32
    Activations Density 0.099%

    No Known Activations