© 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. 518
    Prev
    Next
    INDEX
    Explanations

    companies and businesses

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

    business and organization

    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
    Not in Any Lists

    No Comments

    Negative Logits
    с
    0.52
    .
    0.50
    。
    0.47
     is
    0.45
     be
    0.44
     it
    0.44
     。
    0.43
     它
    0.43
    اي
    0.43
    .。
    0.42
    POSITIVE LOGITS
    ir
    0.64
    im
    0.53
    ill
    0.51
    il
    0.50
    ad
    0.49
    ار
    0.48
    ine
    0.47
    induced
    0.47
    ar
    0.46
    ap
    0.44
    Activations Density 3.089%

    No Known Activations