© 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. 645
    Prev
    Next
    INDEX
    Explanations

    even if, especially the

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

    introducing specific examples

    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
    ları
    0.68
     kawaida
    0.67
     be
    0.66
     ativa
    0.64
    ق
    0.64
     are
    0.64
    ()=>{
    0.63
     altre
    0.63
     as
    0.61
     ahí
    0.61
    POSITIVE LOGITS
    .
    0.84
    t
    0.71
    ام
    0.66
    ت
    0.59
    esters
    0.55
    तः
    0.53
    ان
    0.53
    -
    0.51
    자가
    0.50
    یی
    0.49
    Activations Density 3.839%

    No Known Activations