© 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. 679
    Prev
    Next
    INDEX
    Explanations

    ordering and counting

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

    ordinal numbers and fractions

    np_max-act-logits · claude-4-5-sonnet
    Triggered by @sk5695
    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
    ي
    1.26
    i
    1.01
    is
    0.96
     is
    0.88
     l
    0.87
     ajuda
    0.86
    ك
    0.85
    }$
    0.84
    يت
    0.84
    ;
    0.84
    POSITIVE LOGITS
    ä
    0.78
    وا
    0.75
    ор
    0.71
    ním
    0.71
    ästä
    0.66
    ста
    0.63
    مل
    0.63
    мам
    0.63
     교통
    0.63
    вати
    0.62
    Activations Density 3.403%

    No Known Activations